ALBERT

Description: Encouraged by the recent progress in pedestrian detection, we investigate the gap between current state-of-the-art methods and the “perfect single frame detector”. We enable our analysis by creating a human baseline for pedestrian detection (over the Caltech pedestrian dataset). After manually clustering the frequent errors of a top detector, we characterise both localisation and background-versus-foreground errors. To address localisation errors we study the impact of training annotation noise on the detector performance, and show that we can improve results even with a small portion of sanitised training data. To address background/foreground discrimination, we study convnets for pedestrian detection, and discuss which factors affect their performance. Other than our in-depth analysis, we report top performance on the Caltech pedestrian dataset, and provide a new sanitised set of training and test annotations.

Description: This paper addresses the problem of robust and efficient relative rotation averaging in the context of large-scale Structure from Motion. Relative rotation averaging finds global or absolute rotations for a set of cameras from a set of observed relative rotations between pairs of cameras. We propose a generalized framework of relative rotation averaging that can use different robust loss functions and jointly optimizes for all the unknown camera rotations. Our method uses a quasi-Newton optimization which results in an efficient iteratively reweighted least squares (IRLS) formulation that works in the Lie algebra of the 3D rotation group. We demonstrate the performance of our approach on a number of large-scale data sets. We show that our method outperforms existing methods in the literature both in terms of speed and accuracy.

Description: Speaker diarization consists of assigning speech signals to people engaged in a dialogue. An audio-visual spatiotemporal diarization model is proposed. The model is well suited for challenging scenarios that consist of several participants engaged in multi-party interaction while they move around and turn their heads towards the other participants rather than facing the cameras and the microphones. Multiple-person visual tracking is combined with multiple speech-source localization in order to tackle the speech-to-person association problem. The latter is solved within a novel audio-visual fusion method on the following grounds: binaural spectral features are first extracted from a microphone pair, then a supervised audio-visual alignment technique maps these features onto an image, and finally a semi-supervised clustering method assigns binaural spectral features to visible persons. The main advantage of this method over previous work is that it processes in a principled way speech signals uttered simultaneously by multiple persons. The diarization itself is cast into a latent-variable temporal graphical model that infers speaker identities and speech turns, based on the output of an audio-visual association process, executed at each time slice, and on the dynamics of the diarization variable itself. The proposed formulation yields an efficient exact inference procedure. A novel dataset, that contains audio-visual training data as well as a number of scenarios involving several participants engaged in formal and informal dialogue, is introduced. The proposed method is thoroughly tested and benchmarked with respect to several state-of-the art diarization algorithms.

Description: The capabilities of (I) learning transferable knowledge across domains; and (II) fine-tuning the pre-learned base knowledge towards tasks with considerably smaller data scale are extremely important. Many of the existing transfer learning techniques are supervised approaches, among which deep learning has the demonstrated power of learning domain transferrable knowledge with large scale network trained on massive amounts of labeled data. However, in many biomedical tasks, both the data and the corresponding label can be very limited, where the unsupervised transfer learning capability is urgently needed. In this paper, we proposed a novel multi-scale convolutional sparse coding (MSCSC) method, that (I) automatically learns filter banks at different scales in a joint fashion with enforced scale-specificity of learned patterns; and (II) provides an unsupervised solution for learning transferable base knowledge and fine-tuning it towards target tasks. Extensive experimental evaluation of MSCSC demonstrates the effectiveness of the proposed MSCSC in both regular and transfer learning tasks in various biomedical domains.

Description: Learning visual representations from web data has recently attracted attention for object recognition. Previous studies have mainly focused on overcoming label noise and data bias and have shown promising results by learning directly from web data. However, we argue that it might be better to transfer knowledge from existing human labeling resources to improve performance at nearly no additional cost. In this paper, we propose a new semi-supervised method for learning via web data. Our method has the unique design of exploiting strong supervision, i.e., in addition to standard image-level labels, our method also utilizes detailed annotations including object bounding boxes and part landmarks. By transferring as much knowledge as possible from existing strongly supervised datasets to weakly supervised web images, our method can benefit from sophisticated object recognition algorithms and overcome several typical problems found in webly-supervised learning. We consider the problem of fine-grained visual categorization, in which existing training resources are scarce, as our main research objective. Comprehensive experimentation and extensive analysis demonstrate encouraging performance of the proposed approach, which, at the same time, delivers a new pipeline for fine-grained visual categorization that is likely to be highly effective for real-world applications.

Description: We are motivated by the need for a generic object proposal generation algorithm which achieves good balance between object detection recall, proposal localization quality and computational efficiency. We propose a novel object proposal algorithm, BING++ , which inherits the virtue of good computational efficiency of BING [1] but significantly improves its proposal localization quality. At high level we formulate the problem of object proposal generation from a novel probabilistic perspective, based on which our BING++ manages to improve the localization quality by employing edges and segments to estimate object boundaries and update the proposals sequentially. We propose learning the parameters efficiently by searching for approximate solutions in a quantized parameter space for complexity reduction. We demonstrate the generalization of BING++ with the same fixed parameters across different object classes and datasets. Empirically our BING++ can run at half speed of BING on CPU, but significantly improve the localization quality by 18.5 and 16.7 percent on both VOC2007 and Microhsoft COCO datasets, respectively. Compared with other state-of-the-art approaches, BING++ can achieve comparable performance, but run significantly faster.

Description: Recent years have witnessed the success of deep neural networks in dealing with a plenty of practical problems. Dropout has played an essential role in many successful deep neural networks, by inducing regularization in the model training. In this paper, we present a new regularized training approach: Shakeout. Instead of randomly discarding units as Dropout does at the training stage, Shakeout randomly chooses to enhance or reverse each unit's contribution to the next layer. This minor modification of Dropout has the statistical trait: the regularizer induced by Shakeout adaptively combines $L_{0}$ , $L_{1}$ and $L_{2}$ regularization terms. Our classification experiments with representative deep architectures on image datasets MNIST, CIFAR-10 and ImageNet show that Shakeout deals with over-fitting effectively and outperforms Dropout. We empirically demonstrate that Shakeout leads to sparser weights under both unsupervised and supervised settings. Shakeout also leads to the grouping effect of the input units in a layer. Considering the weights in reflecting the importance of connections, Shakeout is superior to Dropout, which is valuable for the deep model compression. Moreover, we demonstrate that Shakeout can effectively reduce the instability of the training process of the deep architecture.

Description: The goal of this paper is to perform 3D object detection in the context of autonomous driving. Our method aims at generating a set of high-quality 3D object proposals by exploiting stereo imagery. We formulate the problem as minimizing an energy function that encodes object size priors, placement of objects on the ground plane as well as several depth informed features that reason about free space, point cloud densities and distance to the ground. We then exploit a CNN on top of these proposals to perform object detection. In particular, we employ a convolutional neural net (CNN) that exploits context and depth information to jointly regress to 3D bounding box coordinates and object pose. Our experiments show significant performance gains over existing RGB and RGB-D object proposal methods on the challenging KITTI benchmark. When combined with the CNN, our approach outperforms all existing results in object detection and orientation estimation tasks for all three KITTI object classes. Furthermore, we experiment also with the setting where LIDAR information is available, and show that using both LIDAR and stereo leads to the best result.

Description: In this paper, we seek to improve deep neural networks by generalizing the pooling operations that play a central role in the current architectures. We pursue a careful exploration of approaches to allow pooling to learn and to adapt to complex and variable patterns. The two primary directions lie in: (1) learning a pooling function via (two strategies of) combining of max and average pooling, and (2) learning a pooling function in the form of a tree-structured fusion of pooling filters that are themselves learned. In our experiments every generalized pooling operation we explore improves performance when used in place of average or max pooling. We experimentally demonstrate that the proposed pooling operations provide a boost in invariance properties relative to conventional pooling and set the state of the art on several widely adopted benchmark datasets. These benefits come with only a light increase in computational overhead during training (ranging from additional 5 to 15 percent in time complexity) and a very modest increase in the number of model parameters (e.g., additional 1, 9, and 27 parameters for mixed, gated, and 2-level tree pooling operators, respectively). To gain more insights about our proposed pooling methods, we also visualize the learned pooling masks and the embeddings of the internal feature responses for different pooling operations. Our proposed pooling operations are easy to implement and can be applied within various deep neural network architectures.

Description: Graph algorithm is pervasive in many applications ranging from targeted advertising to natural language processing. Recently, Asynchronous Graph Processing (AGP) is becoming a promising model to support graph algorithm on large-scale distributed computing platforms because it enables faster convergence speed and lower synchronization cost than the synchronous model for no barrier between iterations. However, existing AGP methods still suffer from poor performance for inefficient vertex state propagation. In this paper, we propose an effective and low-cost forward and backward sweeping execution method to accelerate state propagation for AGP, based on a key observation that states in AGP can be propagated between vertices much faster when the vertices are processed sequentially along the graph path within each round. Through dividing graph into paths and asynchronously processing vertices on each path in an alternative forward and backward way according to their order on this path, vertex states in our approach can be quickly propagated to other vertices and converge in a faster way with only little additional overhead. In order to efficiently support it over distributed platforms, we also propose a scheme to reduce the communication overhead along with a static priority ordering scheme to further improve the convergence speed. Experimental results on a cluster with 1,024 cores show that our approach achieves excellent scalability for large-scale graph algorithms and the overall execution time is reduced by at least 39.8 percent, in comparison with the most cutting-edge methods.

Description: Deal selection on Groupon is a typical social learning and decision making process, where the quality of a deal is usually unknown to the customers. The customers must acquire this knowledge through social learning from other social medias such as reviews on Yelp. Additionally, the quality of a deal depends on both the state of the vendor and decisions of other customers on Groupon. How social learning and network externality affect the decisions of customers in deal selection on Groupon is our main interest. We develop a data-driven game-theoretic framework to understand the rational deal selection behaviors cross social medias. The sufficient condition of the Nash equilibrium is identified. A value-iteration algorithm is proposed to find the optimal deal selection strategy. We conduct a year-long experiment to trace the competitions among deals on Groupon and the corresponding Yelp ratings. We utilize the dataset to analyze the deal selection game with realistic settings. Finally, the performance of the proposed social learning framework is evaluated with real data. The results suggest that customers do make decisions in a rational way instead of following naive strategies, and there is still room to improve their decisions with assistance from the proposed framework.

Description: Various perceptual domains have underlying compositional semantics that are rarely captured in current models. We suspect this is because directly learning the compositional structure has evaded these models. Yet, the compositional structure of a given domain can be grounded in a separate domain thereby simplifying its learning. To that end, we propose a new approach to modeling bimodal perceptual domains that explicitly relates distinct projections across each modality and then jointly learns a bimodal sparse representation. The resulting model enables compositionality across these distinct projections and hence can generalize to unobserved percepts spanned by this compositional basis. For example, our model can be trained on red triangles and blue squares ; yet, implicitly will also have learned red squares and blue triangles . The structure of the projections and hence the compositional basis is learned automatically; no assumption is made on the ordering of the compositional elements in either modality. Although our modeling paradigm is general, we explicitly focus on a tabletop building-blocks setting. To test our model, we have acquired a new bimodal dataset comprising images and spoken utterances of colored shapes (blocks) in the tabletop setting. Our experiments demonstrate the benefits of explicitly leveraging compositionality in both quantitative and human evaluation studies.

Description: Building upon recent Deep Neural Network architectures, current approaches lying in the intersection of Computer Vision and Natural Language Processing have achieved unprecedented breakthroughs in tasks like automatic captioning or image retrieval. Most of these learning methods, though, rely on large training sets of images associated with human annotations that specifically describe the visual content. In this paper we propose to go a step further and explore the more complex cases where textual descriptions are loosely related to the images. We focus on the particular domain of news articles in which the textual content often expresses connotative and ambiguous relations that are only suggested but not directly inferred from images. We introduce an adaptive CNN architecture that shares most of the structure for multiple tasks including source detection, article illustration and geolocation of articles. Deep Canonical Correlation Analysis is deployed for article illustration, and a new loss function based on Great Circle Distance is proposed for geolocation. Furthermore, we present BreakingNews, a novel dataset with approximately 100K news articles including images, text and captions, and enriched with heterogeneous meta-data (such as GPS coordinates and user comments). We show this dataset to be appropriate to explore all aforementioned problems, for which we provide a baseline performance using various Deep Learning architectures, and different representations of the textual and visual features. We report very promising results and bring to light several limitations of current state-of-the-art in this kind of domain, which we hope will help spur progress in the field.

Description: Machine learning algorithms for the analysis of time-series often depend on the assumption that utilised data are temporally aligned. Any temporal discrepancies arising in the data is certain to lead to ill-generalisable models, which in turn fail to correctly capture properties of the task at hand. The temporal alignment of time-series is thus a crucial challenge manifesting in a multitude of applications. Nevertheless, the vast majority of algorithms oriented towards temporal alignment are either applied directly on the observation space or simply utilise linear projections-thus failing to capture complex, hierarchical non-linear representations that may prove beneficial, especially when dealing with multi-modal data (e.g., visual and acoustic information). To this end, we present Deep Canonical Time Warping (DCTW), a method that automatically learns non-linear representations of multiple time-series that are (i) maximally correlated in a shared subspace, and (ii) temporally aligned. Furthermore, we extend DCTW to a supervised setting, where during training, available labels can be utilised towards enhancing the alignment process. By means of experiments on four datasets, we show that the representations learnt significantly outperform state-of-the-art methods in temporal alignment, elegantly handling scenarios with heterogeneous feature sets, such as the temporal alignment of acoustic and visual information.

Description: Domain adaptation between diverse source and target domains is challenging, especially in the real-world visual recognition tasks where the images and videos consist of significant variations in viewpoints, illuminations, qualities, etc. In this paper, we propose a new approach for domain generalization and domain adaptation based on exemplar SVMs. Specifically, we decompose the source domain into many subdomains, each of which contains only one positive training sample and all negative samples. Each subdomain is relatively less diverse, and is expected to have a simpler distribution. By training one exemplar SVM for each subdomain, we obtain a set of exemplar SVMs. To further exploit the inherent structure of source domain, we introduce a nuclear-norm based regularizer into the objective function in order to enforce the exemplar SVMs to produce a low-rank output on training samples. In the prediction process, the confident exemplar SVM classifiers are selected and reweigted according to the distribution mismatch between each subdomain and the test sample in the target domain. We formulate our approach based on the logistic regression and least square SVM algorithms, which are referred to as low rank exemplar SVMs (LRE-SVMs) and low rank exemplar least square SVMs (LRE-LSSVMs), respectively. A fast algorithm is also developed for accelerating the training of LRE-LSSVMs. We further extend Domain Adaptation Machine (DAM) to learn an optimal target classifier for domain adaptation, and show that our approach can also be applied to domain adaptation with evolving target domain, where the target data distribution is gradually changing. The comprehensive experiments for object recognition and action recognition demonstrate the effectiveness of our approach for domain generalization and domain adaptation with fixed and evolving target domains.

Description: In content-based image retrieval, SIFT feature and the feature from deep convolutional neural network (CNN) have demonstrated promising performance. To fully explore both visual features in a unified framework for effective and efficient retrieval, we propose a collaborative index embedding method to implicitly integrate the index matrices of them. We formulate the index embedding as an optimization problem from the perspective of neighborhood sharing and solve it with an alternating index update scheme. After the iterative embedding, only the embedded CNN index is kept for on-line query, which demonstrates significant gain in retrieval accuracy, with very economical memory cost. Extensive experiments have been conducted on the public datasets with million-scale distractor images. The experimental results reveal that, compared with the recent state-of-the-art retrieval algorithms, our approach achieves competitive accuracy performance with less memory overhead and efficient query computation.

Description: In this paper, we propose a context-aware local binary feature learning (CA-LBFL) method for face recognition. Unlike existing learning-based local face descriptors such as discriminant face descriptor (DFD) and compact binary face descriptor (CBFD) which learn each feature code individually, our CA-LBFL exploits the contextual information of adjacent bits by constraining the number of shifts from different binary bits, so that more robust information can be exploited for face representation. Given a face image, we first extract pixel difference vectors (PDV) in local patches, and learn a discriminative mapping in an unsupervised manner to project each pixel difference vector into a context-aware binary vector. Then, we perform clustering on the learned binary codes to construct a codebook, and extract a histogram feature for each face image with the learned codebook as the final representation. In order to exploit local information from different scales, we propose a context-aware local binary multi-scale feature learning (CA-LBMFL) method to jointly learn multiple projection matrices for face representation. To make the proposed methods applicable for heterogeneous face recognition, we present a coupled CA-LBFL (C-CA-LBFL) method and a coupled CA-LBMFL (C-CA-LBMFL) method to reduce the modality gap of corresponding heterogeneous faces in the feature level, respectively. Extensive experimental results on four widely used face datasets clearly show that our methods outperform most state-of-the-art face descriptors.

Description: Single modality action recognition on RGB or depth sequences has been extensively explored recently. It is generally accepted that each of these two modalities has different strengths and limitations for the task of action recognition. Therefore, analysis of the RGB+D videos can help us to better study the complementary properties of these two types of modalities and achieve higher levels of performance. In this paper, we propose a new deep autoencoder based shared-specific feature factorization network to separate input multimodal signals into a hierarchy of components. Further, based on the structure of the features, a structured sparsity learning machine is proposed which utilizes mixed norms to apply regularization within components and group selection between them for better classification performance. Our experimental results show the effectiveness of our cross-modality feature analysis framework by achieving state-of-the-art accuracy for action classification on five challenging benchmark datasets.

Description: Recently, cross-modal search has attracted considerable attention but remains a very challenging task because of the integration complexity and heterogeneity of the multi-modal data. To address both challenges, in this paper, we propose a novel method termed hetero-manifold regularisation (HMR) to supervise the learning of hash functions for efficient cross-modal search. A hetero-manifold integrates multiple sub-manifolds defined by homogeneous data with the help of cross-modal supervision information. Taking advantages of the hetero-manifold, the similarity between each pair of heterogeneous data could be naturally measured by three order random walks on this hetero-manifold. Furthermore, a novel cumulative distance inequality defined on the hetero-manifold is introduced to avoid the computational difficulty induced by the discreteness of hash codes. By using the inequality, cross-modal hashing is transformed into a problem of hetero-manifold regularised support vector learning. Therefore, the performance of cross-modal search can be significantly improved by seamlessly combining the integrated information of the hetero-manifold and the strong generalisation of the support vector machine. Comprehensive experiments show that the proposed HMR achieve advantageous results over the state-of-the-art methods in several challenging cross-modal tasks.

Description: We propose Multi-Task Learning with Low Rank Attribute Embedding (MTL-LORAE) to address the problem of person re-identification on multi-cameras. Re-identifications on different cameras are considered as related tasks, which allows the shared information among different tasks to be explored to improve the re-identification accuracy. The MTL-LORAE framework integrates low-level features with mid-level attributes as the descriptions for persons. To improve the accuracy of such description, we introduce the low-rank attribute embedding, which maps original binary attributes into a continuous space utilizing the correlative relationship between each pair of attributes. In this way, inaccurate attributes are rectified and missing attributes are recovered. The resulting objective function is constructed with an attribute embedding error and a quadratic loss concerning class labels. It is solved by an alternating optimization strategy. The proposed MTL-LORAE is tested on four datasets and is validated to outperform the existing methods with significant margins.

Description: In the early days, content-based image retrieval (CBIR) was studied with global features. Since 2003, image retrieval based on local descriptors ( de facto SIFT) has been extensively studied for over a decade due to the advantage of SIFT in dealing with image transformations. Recently, image representations based on the convolutional neural network (CNN) have attracted increasing interest in the community and demonstrated impressive performance. Given this time of rapid evolution, this article provides a comprehensive survey of instance retrieval over the last decade. Two broad categories, SIFT-based and CNN-based methods, are presented. For the former, according to the codebook size, we organize the literature into using large/medium-sized/small codebooks. For the latter, we discuss three lines of methods, i.e., using pre-trained or fine-tuned CNN models, and hybrid methods. The first two perform a single-pass of an image to the network, while the last category employs a patch-based feature extraction scheme. This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods. After analyzing and comparing retrieval performance of different categories on several datasets, we discuss promising directions towards generic and specialized instance retrieval.

Description: This paper proposes a method for line segment detection in digital images. We propose a novel linelet-based representation to model intrinsic properties of line segments in rasterized image space. Based on this, line segment detection, validation, and aggregation frameworks are constructed. For a numerical evaluation on real images, we propose a new benchmark dataset of real images with annotated lines called YorkUrban-LineSegment. The results show that the proposed method outperforms state-of-the-art methods numerically and visually. To our best knowledge, this is the first report of numerical evaluation of line segment detection on real images.

Description: This paper introduces a fast and efficient segmentation technique for 2D images and 3D point clouds of building facades. Facades of buildings are highly structured and consequently most methods that have been proposed for this problem aim to make use of this strong prior information. Contrary to most prior work, we are describing a system that is almost domain independent and consists of standard segmentation methods. We train a sequence of boosted decision trees using auto-context features. This is learned using stacked generalization. We find that this technique performs better, or comparable with all previous published methods and present empirical results on all available 2D and 3D facade benchmark datasets. The proposed method is simple to implement, easy to extend, and very efficient at test-time inference.

Description: Super resolving a low-resolution video, namely video super-resolution (SR), is usually handled by either single-image SR or multi-frame SR. Single-Image SR deals with each video frame independently, and ignores intrinsic temporal dependency of video frames which actually plays a very important role in video SR. Multi-Frame SR generally extracts motion information, e.g., optical flow, to model the temporal dependency, but often shows high computational cost. Considering that recurrent neural networks (RNNs) can model long-term temporal dependency of video sequences well, we propose a fully convolutional RNN named bidirectional recurrent convolutional network for efficient multi-frame SR. Different from vanilla RNNs, 1) the commonly-used full feedforward and recurrent connections are replaced with weight-sharing convolutional connections. So they can greatly reduce the large number of network parameters and well model the temporal dependency in a finer level, i.e., patch-based rather than frame-based, and 2) connections from input layers at previous timesteps to the current hidden layer are added by 3D feedforward convolutions, which aim to capture discriminate spatio-temporal patterns for short-term fast-varying motions in local adjacent frames. Due to the cheap convolutional operations, our model has a low computational complexity and runs orders of magnitude faster than other multi-frame SR methods. With the powerful temporal dependency modeling, our model can super resolve videos with complex motions and achieve well performance.

Description: Human faces in surveillance videos often suffer from severe image blur, dramatic pose variations, and occlusion. In this paper, we propose a comprehensive framework based on Convolutional Neural Networks (CNN) to overcome challenges in video-based face recognition (VFR). First, to learn blur-robust face representations, we artificially blur training data composed of clear still images to account for a shortfall in real-world video training data. Using training data composed of both still images and artificially blurred data, CNN is encouraged to learn blur-insensitive features automatically. Second, to enhance robustness of CNN features to pose variations and occlusion, we propose a Trunk-Branch Ensemble CNN model (TBE-CNN), which extracts complementary information from holistic face images and patches cropped around facial components. TBE-CNN is an end-to-end model that extracts features efficiently by sharing the low- and middle-level convolutional layers between the trunk and branch networks. Third, to further promote the discriminative power of the representations learnt by TBE-CNN, we propose an improved triplet loss function. Systematic experiments justify the effectiveness of the proposed techniques. Most impressively, TBE-CNN achieves state-of-the-art performance on three popular video face databases: PaSC, COX Face, and YouTube Faces. With the proposed techniques, we also obtain the first place in the BTAS 2016 Video Person Recognition Evaluation.

Description: RDF question/answering (Q/A) allows users to ask questions in natural languages over a knowledge base represented by RDF. To answer a natural language question, the existing work takes a two-stage approach: question understanding and query evaluation. Their focus is on question understanding to deal with the disambiguation of the natural language phrases. The most common technique is the joint disambiguation, which has the exponential search space. In this paper, we propose a systematic framework to answer natural language questions over RDF repository (RDF Q/A) from a graph data-driven perspective. We propose a semantic query graph to model the query intention in the natural language question in a structural way, based on which, RDF Q/A is reduced to subgraph matching problem. More importantly, we resolve the ambiguity of natural language questions at the time when matches of query are found. The cost of disambiguation is saved if there are no matching found. More specifically, we propose two different frameworks to build the semantic query graph, one is relation (edge)-first and the other one is node-first. We compare our method with some state-of-the-art RDF Q/A systems in the benchmark dataset. Extensive experiments confirm that our method not only improves the precision but also speeds up query performance greatly.

Description: Spatial clustering deals with the unsupervised grouping of places into clusters and finds important applications in urban planning and marketing. Current spatial clustering models disregard information about the people and the time who and when are related to the clustered places. In this paper, we show how the density-based clustering paradigm can be extended to apply on places which are visited by users of a geo-social network. Our model considers spatio-temporal information and the social relationships between users who visit the clustered places. After formally defining the model and the distance measure it relies on, we provide alternatives to our model and the distance measure. We evaluate the effectiveness of our model via a case study on real data; in addition, we design two quantitative measures, called social entropy and community score, to evaluate the quality of the discovered clusters. The results show that temporal-geo-social clusters have special properties and cannot be found by applying simple spatial clustering approaches and other alternatives.

Description: Semantic drift is a common problem in iterative information extraction. Previous approaches for minimizing semantic drift may incur substantial loss in recall. We observe that most semantic drifts are introduced by a small number of questionable extractions in the earlier rounds of iterations. These extractions subsequently introduce a large number of questionable results, which lead to the semantic drift phenomenon. We call these questionable extractions Drifting Points (DPs). If erroneous extractions are the “symptoms” of semantic drift, then DPs are the “causes” of semantic drift. In this paper, we propose a method to minimize semantic drift by identifying the DPs and removing the effect introduced by the DPs. We use isA (concept-instance) extraction as an example to describe our approach in cleaning information extraction errors caused by semantic drift, but we perform experiments on different relation extraction processes on three large real data extraction collections. The experimental results show that our DP cleaning method enables us to clean around 90 percent incorrect instances or patterns with about 90 percent precision, which outperforms the previous approaches we compare with.

Description: Graphs are used for representing and understanding objects and their relationships for numerous applications such as social networks, Semantic Webs, and biological networks. Integrity assurance of data and query results for graph databases is an essential security requirement. In this paper, we propose two efficient integrity verification schemes—HMACs for graphs (gHMAC) for two-party data sharing, and redactable HMACs for graphs (rgHMAC) for third-party data sharing, such as a cloud-based graph database service. We compute one HMAC value for both the schemes and two other verification objects for rgHMAC scheme that are shared with the verifier. We show that the proposed schemes are provably secure with respect to integrity attacks on the structure and/or content of graphs and query results. The proposed schemes have linear complexity in terms of the number of vertices and edges in the graphs, which is shown to be optimal. Our experimental results corroborate that the proposed HMAC-based schemes for graphs are highly efficient as compared to the digital signature-based schemes—computation of HMAC tags is about 10 times faster than the computation of digital signatures.

Description: Reliable propagation of information through large networks, e.g., communication networks, social networks, or sensor networks is very important in many applications concerning marketing, social networks, and wireless sensor networks. However, social ties of friendship may be obsolete, and communication links may fail, inducing the notion of uncertainty in such networks. In this paper, we address the problem of optimizing information propagation in uncertain networks given a constrained budget of edges. We show that this problem requires to solve two NP-hard subproblems: the computation of expected information flow, and the optimal choice of edges. To compute the expected information flow to a source vertex, we propose the F-tree as a specialized data structure, that identifies independent components of the graph for which the information flow can either be computed analytically and efficiently, or for which traditional Monte-Carlo sampling can be applied independently of the remaining network. For the problem of finding the optimal edges, we propose a series of heuristics that exploit properties of this data structure. Our evaluation shows that these heuristics lead to high quality solutions, thus yielding high information flow, while maintaining low running time.

Description: Business to Business (B2B) marketing aims at meeting the needs of other businesses instead of individual consumers, and thus entails management of more complex business needs than consumer marketing. The buying processes of the business customers involve series of different marketing campaigns providing multifaceted information about the products or services. While most existing studies focus on individual consumers, little has been done to guide business customers due to the dynamic and complex nature of these business buying processes. To this end, in this paper, we focus on providing a unified view of social and temporal modeling for B2B marketing campaign recommendation. Along this line, we first exploit the temporal behavior patterns in the B2B buying processes and develop a marketing campaign recommender system. Specifically, we start with constructing a temporal graph as the knowledge representation of the buying process of each business customer. Temporal graph can effectively extract and integrate the campaign order preferences of individual business customers. It is also worth noting that our system is backward compatible since the participating frequency used in conventional static recommender systems is naturally embedded in our temporal graph. The campaign recommender is then built in a low-rank graph reconstruction framework based on probabilistic graphical models. Our framework can identify the common graph patterns and predict missing edges in the temporal graphs. In addition, since business customers very often have different decision makers from the same company, we also incorporate social factors, such as community relationships of the business customers, for further improving overall performances of the missing edge prediction and recommendation. Finally, we have performed extensive empirical studies on real-world B2B marketing data sets and the results show that the proposed method can effectively improve the quality of the campaign recommendat- ons for challenging B2B marketing tasks.

Description: In this paper, we propose a prototype-based classification model for evolving data streams, called SyncStream, which allows dynamically modeling time-changing concepts, making predictions in a local fashion. Instead of learning a single model on a fixed or adaptive sliding window of historical data or ensemble learning a set of weighted base classifiers, SyncStream captures evolving concepts by dynamically maintaining a set of prototypes in a proposed P-Tree, which are obtained based on the error-driven representativeness learning and synchronization-inspired constrained clustering. To identify abrupt concept drifts in data streams, PCA and statistical analysis based heuristic approaches have been introduced. To further learn the associations among distributed data streams, the extended P-Tree structure and KNN-style strategy are introduced. We demonstrate that our new data stream classification approach has several attractive benefits: (a) SyncStream is capable of dynamically modeling the evolving concepts from even a small set of prototypes. (b) Owing to synchronization-based constrained clustering and P-Tree, SyncStream supports efficient and effective data representation and maintenance. (c) SyncStream is also tolerant of inappropriate or noisy examples via error-driven representativeness learning. (d) SyncStream allows learning relationship among distributed data streams at the instance level. The experimental results indicate its efficiency and effectiveness.

Description: Community search is important in graph analysis and can be used in many real applications. In the literature, various community models have been proposed. However, most of them cannot well identify the overlaps between communities which is an essential feature of real graphs. To address this issue, the $k$ -clique percolation community model was proposed and has been proven effective in many applications. Motivated by this, in this paper, we adopt the $k$ -clique percolation community model and study the densest clique percolation community search problem which aims to find the $k$ -clique percolation community with the maximum $k$ value that contains a given set of query nodes. We adopt an index-based approach to solve this problem. Based on the observation that a $k$ -clique percolation community is a union of maximal cliques, we devise a novel compact index, $mathsf {DCPC}$ - $mathsf {Index}$ , to preserve the max- mal cliques and their connectivity information of the input graph. With $mathsf {DCPC}$ - $mathsf {Index}$ , we can answer the densest clique percolation community query efficiently. Besides, we also propose an index construction algorithm based on the definition of $mathsf {DCPC}$ - $mathsf {Index}$ and further improve the algorithm in terms of efficiency and memory consumption. We conduct extensive performance studies on real graphs and the experimental results demonstrate the efficiency of our index-based query processing algorithm and index construction algorithm.

Description: The class imbalance problem in machine learning occurs when certain classes are underrepresented relative to the others, leading to a learning bias toward the majority classes. To cope with the skewed class distribution, many learning methods featuring minority oversampling have been proposed, which are proved to be effective. To reduce information loss during feature space projection, this study proposes a novel oversampling algorithm, named minority oversampling in kernel adaptive subspaces (MOKAS), which exploits the invariant feature extraction capability of a kernel version of the adaptive subspace self-organizing maps. The synthetic instances are generated from well-trained subspaces and then their pre-images are reconstructed in the input space. Additionally, these instances characterize nonlinear structures present in the minority class data distribution and help the learning algorithms to counterbalance the skewed class distribution in a desirable manner. Experimental results on both real and synthetic data show that the proposed MOKAS is capable of modeling complex data distribution and outperforms a set of state-of-the-art oversampling algorithms.

Description: In this paper, we study a novel variant of obstructed nearest neighbor queries, namely, range-based obstructed nearest neighbor (RONN) search. As a natural generalization of continuous obstructed nearest-neighbor (CONN), an RONN query retrieves a set of obstructed nearest neighbors corresponding to every point in a specified range. We propose a new index, namely binary obstructed tree (called OB-tree ), for indexing complex objects in the obstructed space. The novelty of OB-tree lies in the idea of dividing the obstructed space into non-obstructed subspaces , aiming to efficiently retrieve highly qualified candidates for RONN processing. We develop an algorithm for construction of the OB-tree and propose a space division scheme, called optimal obstacle balance (OOB2) scheme, to address the tree balance problem. Accordingly, we propose an efficient algorithm, called RONN by OB-tree Acceleration (RONN-OBA), which exploits the OB-tree and a binary traversal order of data objects to accelerate query processing of RONN. In addition, we extend our work in several aspects regarding the shape of obstacles, and range-based $k$ NN queries in obstructed space. At last, we conduct a comprehensive performance evaluation using both real and synthetic datasets to validate our ideas and the proposed algorithms. The experimental result shows that the RONN-OBA algorithm outperforms the two R-tree based algorithms and RONN-OA significantly.

Description: Existing graph classification usually relies on an exhaustive enumeration of substructure patterns, where the number of substructures expands exponentially w.r.t. with the size of the graph set. Recently, the Weisfeiler-Lehman (WL) graph kernel has achieved the best performance in terms of both accuracy and efficiency among state-of-the-art methods. However, it is still time-consuming, especially for large-scale graph classification tasks. In this paper, we present a -Ary Tree based Hashing (KATH) algorithm, which is able to obtain competitive accuracy with a very fast runtime. The main idea of KATH is to construct a traversal table to quickly approximate the subtree patterns in WL using $K$ -ary trees. Based on the traversal table, KATH employs a recursive indexing process that performs only $r$ times of matrix indexing to generate all $(r-1)$ -depth $K$ -ary trees, where the leaf node labels of a tree can uniquely specify the pattern. After that, the MinHash scheme is used to fingerprint the acquired subtree patterns for a graph. Our experimental results on both real world and synthetic data sets show that KATH runs significantly faster than state-of-the-art methods while achieving competitive or better accuracy.

Description: SimRank is an important measure of vertex-pair similarity according to the structure of graphs. Although progress has been achieved, existing methods still face challenges to handle large graphs. Besides huge index construction and maintenance cost, existing methods may require considerable search space and time overheads in the online SimRank query. In this paper, we design a Monte Carlo based method, UniWalk, to enable the fast top- $k$ SimRank computation over large undirected graphs. UniWalk directly locates the top- $k$ similar vertices for any single source vertex $u$ via $R$ sampling paths originating from $u$ , which avoids selecting candidate vertex set $mathcal{C}$ and the following $O(|mathcal{C}|R)$ bidirectional sampling paths. We also devise a path enumeration strategy to improve the SimRank precision by using path probabilities instead of path frequencies when sampling, a space-efficient method to- reduce intermediate results, and a path-sharing strategy to lower the redundant path sampling cost for multiple source vertices. Furthermore, we extend UniWalk to existing distributed graph processing frameworks to improve its scalability. We conduct extensive experiments to illustrate that UniWalk has high scalability, and outperforms the state-of-the-art methods by orders of magnitude.

Description: Direct Sparse Odometry (DSO) is a visual odometry method based on a novel, highly accurate sparse and direct structure and motion formulation. It combines a fully direct probabilistic model (minimizing a photometric error) with consistent, joint optimization of all model parameters, including geometry-represented as inverse depth in a reference frame-and camera motion. This is achieved in real time by omitting the smoothness prior used in other direct methods and instead sampling pixels evenly throughout the images. Since our method does not depend on keypoint detectors or descriptors, it can naturally sample pixels from across all image regions that have intensity gradient, including edges or smooth intensity variations on essentially featureless walls. The proposed model integrates a full photometric calibration, accounting for exposure time, lens vignetting, and non-linear response functions. We thoroughly evaluate our method on three different datasets comprising several hours of video. The experiments show that the presented approach significantly outperforms state-of-the-art direct and indirect methods in a variety of real-world settings, both in terms of tracking accuracy and robustness.

Description: Given a sequence of snapshots of flu propagating over a population network, can we find a segmentation when the patterns of the disease spread change, possibly due to interventions? In this paper, we study the problem of segmenting graph sequences with labeled nodes. Memes on the Twitter network, diseases over a contact network, movie-cascades over a social network, etc. are all graph sequences with labeled nodes. Most related work on this subject is on plain graphs and hence ignores the label dynamics. Others require fix parameters or feature engineering. We propose SnapNETS , to automatically find segmentations of such graph sequences, with different characteristics of nodes of each label in adjacent segments. It satisfies all the desired properties (being parameter free, comprehensive and scalable) by leveraging a principled, multi-level, flexible framework which maps the problem to a path optimization problem over a weighted DAG. Also, we develop the parallel framework of SnapNETS which speeds up its running time. Finally, we propose an extension of SnapNETS to handle the dynamic graph structures and use it to detect anomalies (and events) in network sequences. Extensive experiments on several diverse real datasets show that it finds cut points matching ground-truth or meaningful external signals and detects anomalies outperforming non-trivial baselines. We also show that the segmentations are easily interpretable, and that SnapNETS scales near-linearly with the size of the input. Finally, we show how to use SnapNETS to detect anomaly in a sequence of dynamic networks.

Description: Document network is a kind of intriguing dataset which can provide both topical (textual content) and topological (relational link) information. A key point in modeling such datasets is to discover proper denominators beneath the text and link. Most previous work introduces the assumption that documents closely linked with each other share common latent topics. However, the heterophily (i.e., tendency to link to different others) of nodes is neglected, which is pervasive in social networks. In this paper, we simultaneously incorporate community detection and topic modeling in a unified framework, and appeal to Canonical Correlation Analysis (CCA) to capture the latent semantic correlations between the two heterogeneous factors, community and topic . Despite of the homophily (i.e., tendency to link to similar others) or heterophily, CCA can properly capture the inherent correlations which fit the dataset itself without any prior hypothesis. We also impose auxiliary word embeddings to improve the quality of topics. The effectiveness of our proposed model is comprehensively verified on three different types of datasets which are hyperlinked networks of web pages, social networks of friends, and coauthor networks of publications. Experimental results show that our approach achieves significant improvements compared with the current state of the art.

Description: The classical K Shortest Paths (KSP) problem, which identifies the $k$ shortest paths in a directed graph, plays an important role in many application domains, such as providing alternative paths for vehicle routing services. However, the returned $k$ shortest paths may be highly similar , i.e., sharing significant amounts of edges, thus adversely affecting service qualities. In this paper, we formalize the K Shortest Paths with Diversity (KSPD) problem that identifies top- $k$ shortest paths such that the paths are dissimilar with each other and the total length of the paths is minimized. We first prove that the KSPD problem is NP-hard and then propose a generic greedy framework to solve the KSPD problem in the sense that (1) it supports a wide variety of path similarity metrics which are widely adopted in the literature and (2) it is also able to efficiently solve the traditional KSP problem if no path similarity metric is specified. The core of the framework includes the use of two judiciously designed lower bounds, where one is dependent on and the other one is independent on the chosen path similarity metric, which effectively reduces the search space and significantly improves efficiency. Empirical studies on five real-world and synthetic graphs and five different path similarity metrics offer insight into the design properties of the proposed general framework and offer evidence that the proposed lower bounds are effective.

Description: Today, many scientific data sets are open to the public. For their operators, it is important to know what the users are interested in. In this paper, we study the problem of extracting and analyzing patterns from the query log of a database. We focus on design errors (antipatterns), which typically lead to unnecessary SQL statements. Such antipatterns do not only have a negative effect on performance. They also introduce bias on any subsequent analysis of the SQL log. We propose a framework designed to discover patterns and antipatterns in arbitrary SQL query logs and to clean antipatterns. To study the usefulness of our approach and to reveal insights regarding the existence of antipatterns in real-world systems, we examine the SQL log of the SkyServer project, containing more than 40 million queries. Among the top 15 patterns, we have found six antipatterns. This result as well as other ones gives way to the conclusion that antipatterns might falsify refactoring and any other downstream analyses.

Description: This paper proposes a new unsupervised spectral feature selection method to preserve both the local and global structure of the features as well as the samples. Specifically, our method uses the self-expressiveness of the features to represent each feature by other features for preserving the local structure of features, and a low-rank constraint on the weight matrix to preserve the global structure among samples as well as features. Our method also proposes to learn the graph matrix measuring the similarity of samples for preserving the local structure among samples. Furthermore, we propose a new optimization algorithm to the resulting objective function, which iteratively updates the graph matrix and the intrinsic space so that collaboratively improving each of them. Experimental analysis on 12 benchmark datasets showed that the proposed method outperformed the state-of-the-art feature selection methods in terms of classification performance.

Description: Generalization is an effective technique for protecting confidential information of individuals, and has been studied by proposing numerous algorithms. However, the previous works do not separate the protection against identity disclosure and sensitive disclosure. Thus, when the requirement of attribute protection is higher than that of identity protection, generalization for $l$ -diversity causes overprotection for identity and large mounts of information utility loss. This paper presents a novel approach, called cross-bucket generalization, as a solution to meet the problem. The rationale is to divide microdata into equivalence groups and buckets. First, it provides separate protection for identity and sensitive values, and the level of protection can be flexibly adjusted based on actual demands. Second, the sizes of equivalence groups and buckets are minimized as far as possible by only satisfying the protection requirements, which avoid the overprotection for identity and reduce information loss. The experiments we conducted illustrate the effectiveness of our solution.

Description: Joint clustering of multiple networks has been shown to be more accurate than performing clustering on individual networks separately. This is because multi-network clustering algorithms typically assume there is a common clustering structure shared by all networks, and different networks can provide compatible and complementary information for uncovering this underlying clustering structure. However, this assumption is too strict to hold in many emerging applications, where multiple networks usually have diverse data distributions. More popularly, the networks in consideration belong to different underlying groups. Only networks in the same underlying group share similar clustering structures. Better clustering performance can be achieved by considering such groups differently. As a result, an ideal method should be able to automatically detect network groups so that networks in the same group share a common clustering structure. To address this problem, we propose a new method, ComClus , to simultaneously group and cluster multiple networks. ComClus is novel in combining the clustering approach of non-negative matrix factorization (NMF) and the feature subspace learning approach of metric learning. Specifically, it treats node clusters as features of networks and learns proper subspaces from such features to differentiate different network groups. During the learning process, the two procedures of network grouping and clustering are coupled and mutually enhanced. Moreover, ComClus can effectively leverage prior knowledge on how to group networks such that network grouping can be conducted in a semi-supervised manner. This will enable users to guide the grouping process using domain knowledge so that network clustering accuracy can be further boosted. Extensive experimental evaluations on a variety of synthetic and real datasets demonstrate the effectiveness and scalability of the proposed method.

Description: Utilizing large-scale GPS data to improve taxi services has become a popular research problem in the areas of data mining, intelligent transportation, geographical information systems, and the Internet of Things. In this paper, we utilize a large-scale GPS data set generated by over 7,000 taxis in a period of one month in Nanjing, China, and propose TaxiRec: a framework for evaluating and discovering the passenger-finding potentials of road clusters, which is incorporated into a recommender system for taxi drivers to seek passengers. In TaxiRec, the underlying road network is first segmented into a number of road clusters, a set of features for each road cluster is extracted from real-life data sets, and then a ranking-based extreme learning machine (ELM) model is proposed to evaluate the passenger-finding potential of each road cluster. In addition, TaxiRec can use this model with a training cluster selection algorithm to provide road cluster recommendations when taxi trajectory data is incomplete or unavailable. Experimental results demonstrate the feasibility and effectiveness of TaxiRec.

Description: Non-negative matrix factorization (NMF) is the problem of determining two non-negative low rank factors $mathbf{W}$ and $mathbf{H}$ , for the given input matrix $mathbf{A}$ , such that $mathbf{A}approx mathbf{W}mathbf{H}$ . NMF is a useful tool for many applications in different domains such as topic modeling in text mining, background separation in video analysis, and community detection in social networks. Despite its popularity in the data mining community, there is a lack of efficient parallel algorithms to solve the problem for big data sets. The main contribution of this work is a new, high-performance parallel computational framework for a broad class of NMF algorithms that iteratively solves alternating non-negative least squares (NLS) subproblems for $mathbf{W}$ and $mathbf{H}$ . It maintains the data and factor matrices in memory (distributed across processors), uses MPI for interprocessor communication, and, in the dense case, provably minimizes communication costs (under mild assumptions). The framework is flexible and able to leverage- a variety of NMF and NLS algorithms, including Multiplicative Update, Hierarchical Alternating Least Squares, and Block Principal Pivoting. Our implementation allows us to benchmark and compare different algorithms on massive dense and sparse data matrices of size that spans from few hundreds of millions to billions. We demonstrate the scalability of our algorithm and compare it with baseline implementations, showing significant performance improvements. The code and the datasets used for conducting the experiments are available online.

Description: Computing shortest distances is a central task in many domains. The growing number of applications dealing with dynamic graphs calls for incremental algorithms, as it is impractical to recompute shortest distances from scratch every time updates occur. In this paper, we address the problem of maintaining all-pairs shortest distances in dynamic graphs. We propose efficient incremental algorithms to process sequences of edge deletions/insertions/updates and vertex deletions/insertions. The proposed approach relies on some general operators that can be easily “instantiated” both in main memory and on top of different underlying DBMSs. We provide complexity analyses of the proposed algorithms. Experimental results on several real-world datasets show that current main-memory algorithms become soon impractical, disk-based ones are needed for larger graphs, and our approach significantly outperforms state-of-the-art algorithms.

Description: Privacy concern in data sharing especially for health data gains particularly increasing attention nowadays. Now, some patients agree to open their information for research use, which gives rise to a new question of how to effectively use the public information to better understand the private dataset without breaching privacy. In this paper, we specialize this question as selecting an optimal subset of the public dataset for M-estimators in the framework of differential privacy (DP) in [1] . From a perspective of non-interactive learning, we first construct the weighted private density estimation from the hybrid datasets under DP. Along the same line as [2] , we analyze the accuracy of the DP M-estimators based on the hybrid datasets. Our main contributions are (i) we find that the bias-variance tradeoff in the performance of our M-estimators can be characterized in the sample size of the released dataset; (ii) based on this finding, we develop an algorithm to select the optimal subset of the public dataset to release under DP. Our simulation studies and application to the real datasets confirm our findings and set a guideline in the real application.

Description: Episode Rule Mining is a popular framework for discovering sequential rules from event sequential data. However, traditional episode rule mining methods only tell that the consequent event is likely to happen within a given time interval after the occurrence of the antecedent events. As a result, they cannot satisfy the requirement of many time sensitive applications, such as program security trading and intelligent transportation management due to the lack of fine-grained response time. In this study, we come up with the concept of fixed-gap episode to address this problem. A fixed-gap episode consists of an ordered set of events where the elapsed time between any two consecutive events is a constant. Based on this concept, we formulate the problem of mining precise-positioning episode rules in which the occurrence time of each event in the consequent is clearly specified. In addition, we develop a trie-based data structure to mine such precise-positioning episode rules with several pruning strategies incorporated for improving the performance as well as reducing memory consumption. Experimental results on real datasets show the superiority of our proposed algorithms.

Description: The problem of deriving lower and upper bounds for the edit distance between undirected, labeled graphs has recently received increasing attention. However, only one algorithm has been proposed that allegedly computes not only an upper but also a lower bound for non-uniform edit costs and incorporates information about both node and edge labels. In this paper, we demonstrate that this algorithm is incorrect. We present a corrected version $mathsf {Bscriptstyle{RANCH}}$ that runs in $mathcal{O}(n^2Delta ^3+n^3)$ time, where $Delta$ is the maximum of the maximum degrees of input graphs $G$ and $H$ . We also develop a speed-up $mathsf {Bscriptstyle{RANCH}}mathsf{Fscriptstyle{AST}}$ that runs in $mathcal{O}(n^2Delta ^2+n^3)$ time and computes an only slightly less accurate lower bound. The lower bounds produced by $maths- {Bscriptstyle{RANCH}}$ and $mathsf {Bscriptstyle{RANCH}}mathsf{Fscriptstyle{AST}}$ are shown to be pseudo-metrics on a collection of graphs. Finally, we suggest an anytime algorithm $mathsf {Bscriptstyle{RANCH}}mathsf{Tscriptstyle{IGHT}}$ that iteratively improves $mathsf {Bscriptstyle{RANCH}}$ ’s lower bound. $mathsf {Bscriptstyle{RANCH}}mathsf{Tscriptstyle{IGHT}}$ runs in $mathcal{O}(n^3Delta ^2+I(n^2Delta ^3+n^3))$ time, where the number of iterations $I$ is controlled by the user. A detailed experimental evaluation shows that all suggested algorithms are Pareto optimal, that they are very effective when used as filters for edit distance range queries, and that they perform excellently when used within classification frameworks.

Description: Clustering of customer transaction data is an important procedure to analyze customer behaviors in retail and e-commerce companies. Note that products from companies are often organized as a product tree, in which the leaf nodes are goods to sell, and the internal nodes (except root node) could be multiple product categories. Based on this tree, we propose the “personalized product tree”, named purchase tree, to represent a customer’s transaction records. So the customers’ transaction data set can be compressed into a set of purchase trees. We propose a partitional clustering algorithm, named PurTreeClust, for fast clustering of purchase trees. A new distance metric is proposed to effectively compute the distance between two purchase trees. To cluster the purchase tree data, we first rank the purchase trees as candidate representative trees with a novel separate density, and then select the top $k$ customers as the representatives of $k$ customer groups. Finally, the clustering results are obtained by assigning each customer to the nearest representative. We also propose a gap statistic based method to evaluate the number of clusters. A series of experiments were conducted on ten real-life transaction data sets, and experimental results show the superior performance of the proposed method.

Description: Database provenance explains how results are derived by queries. However, many use cases such as auditing and debugging of transactions require understanding of how the current state of a database was derived by a transactional history. We present MV-semirings, a provenance model for queries and transactional histories that supports two common multi-version concurrency control protocols: snapshot isolation (SI) and read committed snapshot isolation (RC-SI). Furthermore, we introduce an approach for retroactively capturing such provenance using reenactment , a novel technique for replaying a transactional history with provenance capture. Reenactment exploits the time travel and audit logging capabilities of modern DBMS to replay parts of a transactional history using queries. Importantly, our technique requires no changes to the transactional workload or underlying DBMS and results in only moderate runtime overhead for transactions. We have implemented our approach on top of a commercial DBMS and our experiments confirm that by applying novel optimizations we can efficiently capture provenance for complex transactions over large data sets.

Description: Recognizing human actions from unknown and unseen (novel) views is a challenging problem. We propose a Robust Non-Linear Knowledge Transfer Model (R-NKTM) for human action recognition from novel views. The proposed R-NKTM is a deep fully-connected neural network that transfers knowledge of human actions from any unknown view to a shared high-level virtual view by finding a set of non-linear transformations that connects the views. The R-NKTM is learned from 2D projections of dense trajectories of synthetic 3D human models fitted to real motion capture data and generalizes to real videos of human actions. The strength of our technique is that we learn a single R-NKTM for all actions and all viewpoints for knowledge transfer of any real human action video without the need for re-training or fine-tuning the model. Thus, R-NKTM can efficiently scale to incorporate new action classes. R-NKTM is learned with dummy labels and does not require knowledge of the camera viewpoint at any stage. Experiments on three benchmark cross-view human action datasets show that our method outperforms existing state-of-the-art.

Description: The objective of this work is to detect shadows in images. We pose this as the problem of labeling image regions, where each region corresponds to a group of superpixels. To predict the label of each region, we train a kernel Least-Squares Support Vector Machine (LSSVM) for separating shadow and non-shadow regions. The parameters of the kernel and the classifier are jointly learned to minimize the leave-one-out cross validation error. Optimizing the leave-one-out cross validation error is typically difficult, but it can be done efficiently in our framework. Experiments on two challenging shadow datasets, UCF and UIUC, show that our region classifier outperforms more complex methods. We further enhance the performance of the region classifier by embedding it in a Markov Random Field (MRF) framework and adding pairwise contextual cues. This leads to a method that outperforms the state-of-the-art for shadow detection. In addition we propose a new method for shadow removal based on region relighting. For each shadow region we use a trained classifier to identify a neighboring lit region of the same material. Given a pair of lit-shadow regions we perform a region relighting transformation based on histogram matching of luminance values between the shadow region and the lit region. Once a shadow is detected, we demonstrate that our shadow removal approach produces results that outperform the state of the art by evaluating our method using a publicly available benchmark dataset.

Description: In this paper, we present an attribute grammar for solving two coupled tasks: i) parsing a 2D image into semantic regions; and ii) recovering the 3D scene structures of all regions. The proposed grammar consists of a set of production rules, each describing a kind of spatial relation between planar surfaces in 3D scenes. These production rules are used to decompose an input image into a hierarchical parse graph representation where each graph node indicates a planar surface or a composite surface. Different from other stochastic image grammars, the proposed grammar augments each graph node with a set of attribute variables to depict scene-level global geometry, e.g., camera focal length, or local geometry, e.g., surface normal, contact lines between surfaces. These geometric attributes impose constraints between a node and its off-springs in the parse graph. Under a probabilistic framework, we develop a Markov Chain Monte Carlo method to construct a parse graph that optimizes the 2D image recognition and 3D scene reconstruction purposes simultaneously. We evaluated our method on both public benchmarks and newly collected datasets. Experiments demonstrate that the proposed method is capable of achieving state-of-the-art scene reconstruction of a single image.

Description: Supervised topic models simultaneously model the latent topic structure of large collections of documents and a response variable associated with each document. Existing inference methods are based on variational approximation or Monte Carlo sampling, which often suffers from the local minimum defect. Spectral methods have been applied to learn unsupervised topic models, such as latent Dirichlet allocation (LDA), with provable guarantees. This paper investigates the possibility of applying spectral methods to recover the parameters of supervised LDA (sLDA). We first present a two-stage spectral method, which recovers the parameters of LDA followed by a power update method to recover the regression model parameters. Then, we further present a single-phase spectral algorithm to jointly recover the topic distribution matrix as well as the regression weights. Our spectral algorithms are provably correct and computationally efficient. We prove a sample complexity bound for each algorithm and subsequently derive a sufficient condition for the identifiability of sLDA. Thorough experiments on synthetic and real-world datasets verify the theory and demonstrate the practical effectiveness of the spectral algorithms. In fact, our results on a large-scale review rating dataset demonstrate that our single-phase spectral algorithm alone gets comparable or even better performance than state-of-the-art methods, while previous work on spectral methods has rarely reported such promising performance.

Description: Online multi-object tracking aims at estimating the tracks of multiple objects instantly with each incoming frame and the information provided up to the moment. It still remains a difficult problem in complex scenes, because of the large ambiguity in associating multiple objects in consecutive frames and the low discriminability between objects appearances. In this paper, we propose a robust online multi-object tracking method that can handle these difficulties effectively. We first define the tracklet confidence using the detectability and continuity of a tracklet, and decompose a multi-object tracking problem into small subproblems based on the tracklet confidence. We then solve the online multi-object tracking problem by associating tracklets and detections in different ways according to their confidence values. Based on this strategy, tracklets sequentially grow with online-provided detections, and fragmented tracklets are linked up with others without any iterative and expensive association steps. For more reliable association between tracklets and detections, we also propose a deep appearance learning method to learn a discriminative appearance model from large training datasets, since the conventional appearance learning methods do not provide rich representation that can distinguish multiple objects with large appearance variations. In addition, we combine online transfer learning for improving appearance discriminability by adapting the pre-trained deep model during online tracking. Experiments with challenging public datasets show distinct performance improvement over other state-of-the-arts batch and online tracking methods, and prove the effect and usefulness of the proposed methods for online multi-object tracking.

Description: Active learning is an effective way of engaging users to interactively train models for visual recognition more efficiently. The vast majority of previous works focused on active learning with a single human oracle. The problem of active learning with multiple oracles in a collaborative setting has not been well explored. We present a collaborative computational model for active learning with multiple human oracles, the input from whom may possess different levels of noises. It leads to not only an ensemble kernel machine that is robust to label noises, but also a principled label quality measure to online detect irresponsible labelers. Instead of running independent active learning processes for each individual human oracle, our model captures the inherent correlations among the labelers through shared data among them. Our experiments with both simulated and real crowd-sourced noisy labels demonstrate the efficacy of our model.

Description: Max-trees, or component trees, are graph structures that represent the connected components of an image in a hierarchical way. Nowadays, many application fields rely on images with high-dynamic range or floating point values. Efficient sequential algorithms exist to build trees and compute attributes for images of any bit depth. However, we show that the current parallel algorithms perform poorly already with integers at bit depths higher than 16 bits per pixel. We propose a parallel method combining the two worlds of flooding and merging max-tree algorithms. First, a pilot max-tree of a quantized version of the image is built in parallel using a flooding method. Later, this structure is used in a parallel leaf-to-root approach to compute efficiently the final max-tree and to drive the merging of the sub-trees computed by the threads. We present an analysis of the performance both on simulated and actual 2D images and 3D volumes. Execution times are about $20times$ better than the fastest sequential algorithm and speed-up goes up to $30-40$ on 64 threads.

Description: Accompanied with the rising popularity of compressed sensing, the Alternating Direction Method of Multipliers (ADMM) has become the most widely used solver for linearly constrained convex problems with separable objectives. In this work, we observe that many existing ADMMs update the primal variable by minimizing different majorant functions with their convergence proofs given case by case. Inspired by the principle of majorization minimization, we respectively present the unified frameworks of Gauss-Seidel ADMMs and Jacobian ADMMs, which use different historical information for the current updating. Our frameworks generalize previous ADMMs to solve the problems with non-separable objectives. We also show that ADMMs converge faster when the used majorant function is tighter. We then propose the Mixed Gauss-Seidel and Jacobian ADMM (M-ADMM) which alleviates the slow convergence issue of Jacobian ADMMs by absorbing merits of the Gauss-Seidel ADMMs. M-ADMM can be further improved by backtracking and wise variable partition. We also propose to solve the multi-blocks problems by Proximal Gauss-Seidel ADMM which is of the Gauss-Seidel type. It convegences for non-strongly convex objective. Experiments on both synthesized and real-world data demonstrate the superiority of our new ADMMs. Finally, we release a toolbox that implements efficient ADMMs for many problems in compressed sensing.

Description: We propose a novel approach to generate a binary descriptor optimized for each image patch independently. The approach is inspired by the linear discriminant embedding that simultaneously increases inter and decreases intra class distances. A set of discriminative and uncorrelated binary tests is established from all possible tests in an offline training process. The patch adapted descriptors are then efficiently built online from a subset of features which lead to lower intra-class distances and thus, to a more robust descriptor. We perform experiments on three widely used benchmarks and demonstrate improvements in matching performance, and illustrate that per-patch optimization outperforms global optimization.

Description: The objective of this paper is to design an embedding method that maps local features describing an image (e.g., SIFT) to a higher dimensional representation useful for the image retrieval problem. First, motivated by the relationship between the linear approximation of a nonlinear function in high dimensional space and the state-of-the-art feature representation used in image retrieval, i.e., VLAD, we propose a new approach for the approximation. The embedded vectors resulted by the function approximation process are then aggregated to form a single representation for image retrieval. Second, in order to make the proposed embedding method applicable to large scale problem, we further derive its fast version in which the embedded vectors can be efficiently computed, i.e., in the closed-form. We compare the proposed embedding methods with the state of the art in the context of image search under various settings: when the images are represented by medium length vectors, short vectors, or binary vectors. The experimental results show that the proposed embedding methods outperform existing the state of the art on the standard public image retrieval benchmarks.

Description: Median filtering is among the most utilized tools for smoothing real-valued data, as it is robust, edge-preserving, value-preserving, and yet can be computed efficiently. For data living on the unit circle, such as phase data or orientation data, a filter with similar properties is desirable. For these data, there is no unique means to define a median; so we discuss various possibilities. The arc distance median turns out to be the only variant which leads to robust, edge-preserving and value-preserving smoothing. However, there are no efficient algorithms for filtering based on the arc distance median. Here, we propose fast algorithms for filtering of signals and images with values on the unit circle based on the arc distance median. For non-quantized data, we develop an algorithm that scales linearly with the filter size. The runtime of our reference implementation is only moderately higher than the Matlab implementation of the classical median filter for real-valued data. For quantized data, we obtain an algorithm of constant complexity w.r.t. the filter size. We demonstrate the performance of our algorithms for real life data sets: phase images from interferometric synthetic aperture radar, planar flow fields from optical flow, and time series of wind directions.

Description: Multi-object tracking has been studied for decades. However, when it comes to tracking pedestrians in extremely crowded scenes, we are limited to only few works. This is an important problem which gives rise to several challenges. Pre-trained object detectors fail to localize targets in crowded sequences. This consequently limits the use of data-association based multi-target tracking methods which rely on the outcome of an object detector. Additionally, the small apparent target size makes it challenging to extract features to discriminate targets from their surroundings. Finally, the large number of targets greatly increases computational complexity which in turn makes it hard to extend existing multi-target tracking approaches to high-density crowd scenarios. In this paper, we propose a tracker that addresses the aforementioned problems and is capable of tracking hundreds of people efficiently. We formulate online crowd tracking as Binary Quadratic Programing. Our formulation employs target's individual information in the form of appearance and motion as well as contextual cues in the form of neighborhood motion, spatial proximity and grouping, and solves detection and data association simultaneously. In order to solve the proposed quadratic optimization efficiently, where state-of art commercial quadratic programing solvers fail to find the solution in a reasonable amount of time, we propose to use the most recent version of the Modified Frank Wolfe algorithm, which takes advantage of SWAP-steps to speed up the optimization. We show that the proposed formulation can track hundreds of targets efficiently and improves state-of-art results by significant margins on eleven challenging high density crowd sequences.

Description: Superpixels are perceptually meaningful atomic regions that can effectively capture image features. Among various methods for computing uniform superpixels, simple linear iterative clustering (SLIC) is popular due to its simplicity and high performance. In this paper, we extend SLIC to compute content-sensitive superpixels, i.e., small superpixels in content-dense regions with high intensity or colour variation and large superpixels in content-sparse regions. Rather than using the conventional SLIC method that clusters pixels in $mathbb {R}^5$ , we map the input image $I$ to a 2-dimensional manifold $mathcal {M}subset mathbb {R}^5$ , whose area elements are a good measure of the content density in $I$ . We propose a simple method, called intrinsic manifold SLIC (IMSLIC), for computing a geodesic centroidal Voronoi tessellation (GCVT)—a uniform tessellation—on $mathcal {M}$ , which induces the content-sensitive superpixels in $I$ . In contrast to the existing algorithms, IMSLIC characterizes the content sensitivity b- measuring areas of Voronoi cells on $mathcal {M}$ . Using a simple and fast approximation to a closed-form solution, the method can compute the GCVT at a very low cost and guarantees that all Voronoi cells are simply connected. We thoroughly evaluate IMSLIC and compare it with eleven representative methods on the BSDS500 dataset and seven representative methods on the NYUV2 dataset. Computational results show that IMSLIC outperforms existing methods in terms of commonly used quality measures pertaining to superpixels such as compactness, adherence to boundaries, and achievable segmentation accuracy. We also evaluate IMSLIC and seven representative methods in an image contour closure application, and the results on two datasets, WHD and WSD, show that IMSLIC achieves the best foreground segmentation performance.

Description: Light-field cameras have recently emerged as a powerful tool for one-shot passive 3D shape capture. However, obtaining the shape of glossy objects like metals or plastics remains challenging, since standard Lambertian cues like photo-consistency cannot be easily applied. In this paper, we derive a spatially-varying (SV)BRDF-invariant theory for recovering 3D shape and reflectance from light-field cameras. Our key theoretical insight is a novel analysis of diffuse plus single-lobe SVBRDFs under a light-field setup. We show that, although direct shape recovery is not possible, an equation relating depths and normals can still be derived. Using this equation, we then propose using a polynomial (quadratic) shape prior to resolve the shape ambiguity. Once shape is estimated, we also recover the reflectance. We present extensive synthetic data on the entire MERL BRDF dataset, as well as a number of real examples to validate the theory, where we simultaneously recover shape and BRDFs from a single image taken with a Lytro Illum camera.

Description: We propose a novel approach to reconstructing curvilinear tree structures evolving over time, such as road networks in 2D aerial images or neural structures in 3D microscopy stacks acquired in vivo . To enforce temporal consistency, we simultaneously process all images in a sequence, as opposed to reconstructing structures of interest in each image independently. We formulate the problem as a Quadratic Mixed Integer Program and demonstrate the additional robustness that comes from using all available visual clues at once, instead of working frame by frame. Furthermore, when the linear structures undergo local changes over time, our approach automatically detects them.

Description: It is often desirable to be able to recognize when inputs to a recognition function learned in a supervised manner correspond to classes unseen at training time. With this ability, new class labels could be assigned to these inputs by a human operator, allowing them to be incorporated into the recognition function—ideally under an efficient incremental update mechanism. While good algorithms that assume inputs from a fixed set of classes exist, e.g. , artificial neural networks and kernel machines, it is not immediately obvious how to extend them to perform incremental learning in the presence of unknown query classes. Existing algorithms take little to no distributional information into account when learning recognition functions and lack a strong theoretical foundation. We address this gap by formulating a novel, theoretically sound classifier—the Extreme Value Machine (EVM). The EVM has a well-grounded interpretation derived from statistical Extreme Value Theory (EVT), and is the first classifier to be able to perform nonlinear kernel-free variable bandwidth incremental learning. Compared to other classifiers in the same deep network derived feature space, the EVM is accurate and efficient on an established benchmark partition of the ImageNet dataset.

Description: Video text extraction plays an important role for multimedia understanding and retrieval. Most previous research efforts are conducted within individual frames. A few of recent methods, which pay attention to text tracking using multiple frames, however, do not effectively mine the relations among text detection, tracking and recognition. In this paper, we propose a generic Bayesian-based framework of Tracking based Text Detection And Recognition (T $^2$ DAR) from web videos for embedded captions, which is composed of three major components, i.e., text tracking, tracking based text detection, and tracking based text recognition. In this unified framework, text tracking is first conducted by tracking-by-detection. Tracking trajectories are then revised and refined with detection or recognition results. Text detection or recognition is finally improved with multi-frame integration. Moreover, a challenging video text (embedded caption text) database (USTB-VidTEXT) is constructed and publicly available. A variety of experiments on this dataset verify that our proposed approach largely improves the performance of text detection and recognition from web videos.

Description: We propose a novel minimal path method for the segmentation of 2D and 3D line structures. Minimal path methods perform propagation of a wavefront emanating from a start point at a speed derived from image features, followed by path extraction using backtracing. Usually, the computation of the speed and the propagation of the wave are two separate steps, and point features are used to compute a static speed. We introduce a new continuous minimal path method which steers the wave propagation progressively using dynamic speed based on path features . We present three instances of our method, using an appearance feature of the path, a geometric feature based on the curvature of the path, and a joint appearance and geometric feature based on the tangent of the wavefront. These features have not been used in previous continuous minimal path methods. We compute the features dynamically during the wave propagation, and also efficiently using a fast numerical scheme and a low-dimensional parameter space. Our method does not suffer from discretization or metrication errors. We performed qualitative and quantitative evaluations using 2D and 3D images from different application areas.

Description: Presents the table of contents for this issue of the publication.

Description: Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.

Description: Given a large collection of unlabeled face images, we address the problem of clustering faces into an unknown number of identities. This problem is of interest in social media, law enforcement, and other applications, where the number of faces can be of the order of hundreds of million, while the number of identities (clusters) can range from a few thousand to millions. To address the challenges of run-time complexity and cluster quality, we present an approximate Rank-Order clustering algorithm that performs better than popular clustering algorithms (k-Means and Spectral). Our experiments include clustering up to 123 million face images into over 10 million clusters. Clustering results are analyzed in terms of external (known face labels) and internal (unknown face labels) quality measures, and run-time. Our algorithm achieves an F-measure of 0.87 on the LFW benchmark (13 K faces of 5,749 individuals), which drops to 0.27 on the largest dataset considered (13 K faces in LFW + 123M distractor images). Additionally, we show that frames in the YouTube benchmark can be clustered with an F-measure of 0.71. An internal per-cluster quality measure is developed to rank individual clusters for manual exploration of high quality clusters that are compact and isolated.

Description: Deep unfolding provides an approach to integrate the probabilistic generative models and the deterministic neural networks. Such an approach is benefited by deep representation, easy interpretation, flexible learning and stochastic modeling. This study develops the unsupervised and supervised learning of deep unfolded topic models for document representation and classification. Conventionally, the unsupervised and supervised topic models are inferred via the variational inference algorithm where the model parameters are estimated by maximizing the lower bound of logarithm of marginal likelihood using input documents without and with class labels, respectively. The representation capability or classification accuracy is constrained by the variational lower bound and the tied model parameters across inference procedure. This paper aims to relax these constraints by directly maximizing the end performance criterion and continuously untying the parameters in learning process via deep unfolding inference (DUI). The inference procedure is treated as the layer-wise learning in a deep neural network. The end performance is iteratively improved by using the estimated topic parameters according to the exponentiated updates. Deep learning of topic models is therefore implemented through a back-propagation procedure. Experimental results show the merits of DUI with increasing number of layers compared with variational inference in unsupervised as well as supervised topic models.

Description: Biometrics is the technique of automatically recognizing individuals based on their biological or behavioral characteristics. Various biometric traits have been introduced and widely investigated, including fingerprint, iris, face, voice, palmprint, gait and so forth. Apart from identity, biometric data may convey various other personal information, covering affect, age, gender, race, accent, handedness, height, weight, etc. Among these, analysis of demographics (age, gender, and race) has received tremendous attention owing to its wide real-world applications, with significant efforts devoted and great progress achieved. This survey first presents biometric demographic analysis from the standpoint of human perception, then provides a comprehensive overview of state-of-the-art advances in automated estimation from both academia and industry. Despite these advances, a number of challenging issues continue to inhibit its full potential. We second discuss these open problems, and finally provide an outlook into the future of this very active field of research by sharing some promising opportunities.

Description: In this paper, we investigate and exploit the influence of facial expressions on automatic age estimation. Different from existing approaches, our method jointly learns the age and expression by introducing a new graphical model with a latent layer between the age/expression labels and the features. This layer aims to learn the relationship between the age and expression and captures the face changes which induce the aging and expression appearance, and thus obtaining expression-invariant age estimation. Conducted on three age-expression datasets (FACES [1] , Lifespan [2] and NEMO [3] ), our experiments illustrate the improvement in performance when the age is jointly learnt with expression in comparison to expression-independent age estimation. The age estimation error is reduced by 14.43, 37.75 and 9.30 percent for the FACES, Lifespan and NEMO datasets respectively. The results obtained by our graphical model, without prior-knowledge of the expressions of the tested faces, are better than the best reported ones for all datasets. The flexibility of the proposed model to include more cues is explored by incorporating gender together with age and expression. The results show performance improvements for all cues.

Description: Nearest neighbor search is a problem of finding the data points from the database such that the distances from them to the query point are the smallest. Learning to hash is one of the major solutions to this problem and has been widely studied recently. In this paper, we present a comprehensive survey of the learning to hash algorithms, categorize them according to the manners of preserving the similarities into: pairwise similarity preserving, multiwise similarity preserving, implicit similarity preserving, as well as quantization, and discuss their relations. We separate quantization from pairwise similarity preserving as the objective function is very different though quantization, as we show, can be derived from preserving the pairwise similarities. In addition, we present the evaluation protocols, and the general performance analysis, and point out that the quantization algorithms perform superiorly in terms of search accuracy, search time cost, and space cost. Finally, we introduce a few emerging topics.

Description: Graph matching is essential in several fields that use structured information, such as biology, chemistry, social networks, knowledge management, document analysis and others. Except for special classes of graphs, graph matching has in the worst-case an exponential complexity; however, there are algorithms that show an acceptable execution time, as long as the graphs are not too large and not too dense. In this paper we introduce a novel subgraph isomorphism algorithm, VF3, particularly efficient in the challenging case of graphs with thousands of nodes and a high edge density. Its performance, both in terms of time and memory, has been assessed on a large dataset of 12,700 random graphs with a size up to 10,000 nodes, made publicly available. VF3 has been compared with four other state-of-the-art algorithms, and the huge experimentation required more than two years of processing time. The results confirm that VF3 definitely outperforms the other algorithms when the graphs become huge and dense, but also has a very good performance on smaller or sparser graphs.

Description: Pose variation remains to be a major challenge for real-world face recognition. We approach this problem through a probabilistic elastic part model. We extract local descriptors (e.g., LBP or SIFT) from densely sampled multi-scale image patches. By augmenting each descriptor with its location, a Gaussian mixture model (GMM) is trained to capture the spatial-appearance distribution of the face parts of all face images in the training corpus, namely the probabilistic elastic part (PEP) model. Each mixture component of the GMM is confined to be a spherical Gaussian to balance the influence of the appearance and the location terms, which naturally defines a part. Given one or multiple face images of the same subject, the PEP-model builds its PEP representation by sequentially concatenating descriptors identified by each Gaussian component in a maximum likelihood sense. We further propose a joint Bayesian adaptation algorithm to adapt the universally trained GMM to better model the pose variations between the target pair of faces/face tracks, which consistently improves face verification accuracy. Our experiments show that we achieve state-of-the-art face verification accuracy with the proposed representations on the Labeled Face in the Wild (LFW) dataset, the YouTube video face database, and the CMU MultiPIE dataset.

Description: We present Convolutional Oriented Boundaries (COB), which produces multiscale oriented contours and region hierarchies starting from generic image classification Convolutional Neural Networks (CNNs). COB is computationally efficient, because it requires a single CNN forward pass for multi-scale contour detection and it uses a novel sparse boundary representation for hierarchical segmentation; it gives a significant leap in performance over the state-of-the-art, and it generalizes very well to unseen categories and datasets. Particularly, we show that learning to estimate not only contour strength but also orientation provides more accurate results. We perform extensive experiments for low-level applications on BSDS, PASCAL Context, PASCAL Segmentation, and NYUD to evaluate boundary detection performance, showing that COB provides state-of-the-art contours and region hierarchies in all datasets. We also evaluate COB on high-level tasks when coupled with multiple pipelines for object proposals, semantic contours, semantic segmentation, and object detection on MS-COCO, SBD, and PASCAL; showing that COB also improves the results for all tasks.

Description: Inferring a probability density function (pdf) for shape from a population of point sets is a challenging problem. The lack of point-to-point correspondences and the non-linearity of the shape spaces undermine the linear models. Methods based on manifolds model the shape variations naturally, however, statistics are often limited to a single geodesic mean and an arbitrary number of variation modes. We relax the manifold assumption and consider a piece-wise linear form, implementing a mixture of distinctive shape classes. The pdf for point sets is defined hierarchically, modeling a mixture of Probabilistic Principal Component Analyzers (PPCA) in higher dimension. A Variational Bayesian approach is designed for unsupervised learning of the posteriors of point set labels, local variation modes, and point correspondences. By maximizing the model evidence, the numbers of clusters, modes of variations, and points on the mean models are automatically selected. Using the predictive distribution, we project a test shape to the spaces spanned by the local PPCA's. The method is applied to point sets from: i) synthetic data, ii) healthy versus pathological heart morphologies, and iii) lumbar vertebrae. The proposed method selects models with expected numbers of clusters and variation modes, achieving lower generalization-specificity errors compared to state-of-the-art.

Description: We propose an approach for retrieving a sequence of natural sentences for an image stream. Since general users often take a series of pictures on their experiences, much online visual information exists in the form of image streams, for which it would better take into consideration of the whole image stream to produce natural language descriptions. While almost all previous studies have dealt with the relation between a single image and a single natural sentence, our work extends both input and output dimension to a sequence of images and a sequence of sentences. For retrieving a coherent flow of multiple sentences for a photo stream, we propose a multimodal neural architecture called coherence recurrent convolutional network (CRCN), which consists of convolutional neural networks, bidirectional long short-term memory (LSTM) networks, and an entity-based local coherence model. Our approach directly learns from vast user-generated resource of blog posts as text-image parallel training data. We collect more than 22 K unique blog posts with 170 K associated images for the travel topics of NYC , Disneyland , Australia , and Hawaii . We demonstrate that our approach outperforms other state-of-the-art image captioning methods for text sequence generation, using both quantitative measures and user studies via Amazon Mechanical Turk.

Description: sGLOH (shifting GLOH) is a histogram-based keypoint descriptor that can be associated to multiple quantized rotations of the keypoint patch without any recomputation. This property can be exploited to define the best distance between two descriptor vectors, thus avoiding computing the dominant orientation. In addition, sGLOH can reject incongruous correspondences by adding a global constraint on the rotations either as an a priori knowledge or based on the data. This paper thoroughly reconsiders sGLOH and improves it in terms of robustness, speed and descriptor dimension. The revised sGLOH embeds more quantized rotations, thus yielding more correct matches. A novel fast matching scheme is also designed, which significantly reduces both computation time and memory usage. In addition, a new binarization technique based on comparisons inside each descriptor histogram is defined, yielding a more compact, faster, yet robust alternative. Results on an exhaustive comparative experimental evaluation show that the revised sGLOH descriptor incorporating the above ideas and combining them according to task requirements, improves in most cases the state of the art in both image matching and object recognition.

Description: We propose a new method to add an uncalibrated node into a network of calibrated cameras using only pairwise point correspondences. While previous methods perform this task using triple correspondences, these are often difficult to establish when there is limited overlap between different views. In such challenging cases we must rely on pairwise correspondences and our solution becomes more advantageous. Our method includes an 11-point minimal solution for the intrinsic and extrinsic calibration of a camera from pairwise correspondences with other two calibrated cameras, and a new inlier selection framework that extends the traditional RANSAC family of algorithms to sampling across multiple datasets. Our method is validated on different application scenarios where a lack of triple correspondences might occur: addition of a new node to a camera network; calibration and motion estimation of a moving camera inside a camera network; and addition of views with limited overlap to a Structure-from-Motion model.

Description: In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First , we highlight convolution with upsampled filters, or ‘atrous convolution’, as a powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively enlarge the field of view of filters to incorporate larger context without increasing the number of parameters or the amount of computation. Second , we propose atrous spatial pyramid pooling (ASPP) to robustly segment objects at multiple scales. ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multiple scales. Third , we improve the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. The commonly deployed combination of max-pooling and downsampling in DCNNs achieves invariance but has a toll on localization accuracy. We overcome this by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF), which is shown both qualitatively and quantitatively to improve localization performance. Our proposed “DeepLab” system sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 79.7 percent mIOU in the test set, and advances the results on three other datasets: PASCAL-Context, PASCAL-Person-Part, and Cityscapes. All of our code is made publicly available online.

Description: Age progression is defined as aesthetically re-rendering the aging face at any future age for an individual face. In this work, we aim to automatically render aging faces in a personalized way. Basically, for each age group, we learn an aging dictionary to reveal its aging characteristics (e.g., wrinkles), where the dictionary bases corresponding to the same index yet from two neighboring aging dictionaries form a particular aging pattern cross these two age groups, and a linear combination of all these patterns expresses a particular personalized aging process. Moreover, two factors are taken into consideration in the dictionary learning process. First, beyond the aging dictionaries, each person may have extra personalized facial characteristics, e.g., mole, which are invariant in the aging process. Second, it is challenging or even impossible to collect faces of all age groups for a particular person, yet much easier and more practical to get face pairs from neighboring age groups. To this end, we propose a novel Bi-level Dictionary Learning based Personalized Age Progression (BDL-PAP) method. Here, bi-level dictionary learning is formulated to learn the aging dictionaries based on face pairs from neighboring age groups. Extensive experiments well demonstrate the advantages of the proposed BDL-PAP over other state-of-the-arts in term of personalized age progression, as well as the performance gain for cross-age face verification by synthesizing aging faces.

Description: Face alignment acts as an important task in computer vision. Regression-based methods currently dominate the approach to solving this problem, which generally employ a series of mapping functions from the face appearance to iteratively update the face shape hypothesis. One keypoint here is thus how to perform the regression procedure. In this work, we formulate this regression procedure as a sparse coding problem. We learn two relational dictionaries, one for the face appearance and the other one for the face shape, with coupled reconstruction coefficient to capture their underlying relationships. To deploy this model for face alignment, we derive the relational dictionaries in a stage-wised manner to perform close-loop refinement of themselves, i.e., the face appearance dictionary is first learned from the face shape dictionary and then used to update the face shape hypothesis, and the updated face shape dictionary from the shape hypothesis is in return used to refine the face appearance dictionary. To improve the model accuracy, we extend this model hierarchically from the whole face shape to face part shapes, thus both the global and local view variations of a face are captured. To locate facial landmarks under occlusions, we further introduce an occlusion dictionary into the face appearance dictionary to recover face shape from partially occluded face appearance. The occlusion dictionary is learned in a data driven manner from background images to represent a set of elemental occlusion patterns, a sparse combination of which models various practical partial face occlusions. By integrating all these technical innovations, we obtain a robust and accurate approach to locate facial landmarks under different face views and possibly severe occlusions for face images in the wild. Extensive experimental analyses and evaluations on different benchmark datasets, as well as two new datasets built by ourselves, have demonstrated the robustness and accuracy of our proposed - odel, especially for face images with large view variations and/or severe occlusions.