Search

The Tsetlin Machine (TM) is a recent machine learning algorithm with several distinct properties, such as interpretability, simplicity, and hardware-friendliness. Although numerous empirical evaluations report on its performance, the mathematical analysis of its convergence is still open. In this article, we analyze the convergence of the TM with only one clause involved for classification. More specifically, we examine two basic logical operators, namely, the "IDENTITY"- and "NOT" operators. Our analysis reveals that the TM, with just one clause, can converge correctly to the intended logical operator, learning from training data over an infinite time horizon. Besides, it can capture arbitrarily rare patterns and select the most accurate one when two candidate patterns are incompatible, by configuring a granularity parameter. The analysis of the convergence of the two basic operators lays the foundation for analyzing other logical operators. These analyses altogether, from a mathematical perspective, provide new insights on why TMs have obtained state-of-the-art performance on several pattern recognition problems., Comment: 23 pages, 10 figures

Three-dimensional Morphable Models (3DMMs) are powerful statistical tools for representing the 3D shapes and textures of an object class. Here we present the most complete 3DMM of the human head to date that includes face, cranium, ears, eyes, teeth and tongue. To achieve this, we propose two methods for combining existing 3DMMs of different overlapping head parts: i. use a regressor to complete missing parts of one model using the other, ii. use the Gaussian Process framework to blend covariance matrices from multiple models. Thus we build a new combined face-and-head shape model that blends the variability and facial detail of an existing face model (the LSFM) with the full head modelling capability of an existing head model (the LYHM). Then we construct and fuse a highly-detailed ear model to extend the variation of the ear shape. Eye and eye region models are incorporated into the head model, along with basic models of the teeth, tongue and inner mouth cavity. The new model achieves state-of-the-art performance. We use our model to reconstruct full head representations from single, unconstrained images allowing us to parameterize craniofacial shape and texture, along with the ear shape, eye gaze and eye color., 18 pages, 18 figures, submitted to Transactions on Pattern Analysis and Machine Intelligence (TPAMI) on the 9th of October as an extension paper of the original oral CVPR paper : arXiv:1903.03785

In this work, we aim to address the problem of human interaction recognition in videos by exploring the long-term inter-related dynamics among multiple persons. Recently, Long Short-Term Memory (LSTM) has become a popular choice to model individual dynamic for single-person action recognition due to its ability to capture the temporal motion information in a range. However, most existing LSTM-based methods focus only on capturing the dynamics of human interaction by simply combining all dynamics of individuals or modeling them as a whole. Such methods neglect the inter-related dynamics of how human interactions change over time. To this end, we propose a novel Hierarchical Long Short-Term Concurrent Memory (H-LSTCM) to model the long-term inter-related dynamics among a group of persons for recognizing human interactions. Specifically, we first feed each person's static features into a Single-Person LSTM to model the single-person dynamic. Subsequently, at one time step, the outputs of all Single-Person LSTM units are fed into a novel Concurrent LSTM (Co-LSTM) unit, which mainly consists of multiple sub-memory units, a new cell gate, and a new co-memory cell. In the Co-LSTM unit, each sub-memory unit stores individual motion information, while this Co-LSTM unit selectively integrates and stores inter-related motion information between multiple interacting persons from multiple sub-memory units via the cell gate and co-memory cell, respectively. Extensive experiments on several public datasets validate the effectiveness of the proposed H-LSTCM by comparing against baseline and state-of-the-art methods.

Spiking neural networks (SNNs) have shown clear advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency, due to their event-driven nature and sparse communication. However, the training of deep SNNs is not straightforward. In this paper, we propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition, which is referred to as progressive tandem learning. By studying the equivalence between ANNs and SNNs in the discrete representation space, a primitive network conversion method is introduced that takes full advantage of spike count to approximate the activation value of ANN neurons. To compensate for the approximation errors arising from the primitive network conversion, we further introduce a layer-wise learning method with an adaptive training scheduler to fine-tune the network weights. The progressive tandem learning framework also allows hardware constraints, such as limited weight precision and fan-in connections, to be progressively imposed during training. The SNNs thus trained have demonstrated remarkable classification and regression capabilities on large-scale object recognition, image reconstruction, and speech separation tasks, while requiring at least an order of magnitude reduced inference time and synaptic operations than other state-of-the-art SNN implementations. It, therefore, opens up a myriad of opportunities for pervasive mobile and embedded devices with a limited power budget.

Kinship verification is a very important technique in many real-world applications, e.g., personal album organization, missing person investigation and forensic analysis. However, it is extremely difficult to verify a family pair with generation gap, e.g., father and son, since there exist both age gap and identity variation. It is essential to well fight off such challenges to achieve promising kinship verification performance. To this end, we propose a towards-young cross-generation model for effective kinship verification by mitigating both age and identity divergences. Specifically, we explore a conditional generative model to bring in an intermediate domain to bridge each pair. Thus, we could extract more effective features through deep architectures with a newly-designed Sparse Discriminative Metric Loss (SDM-Loss), which is exploited to involve the positive and negative information. Experimental results on kinship benchmark demonstrate the superiority of our proposed model by comparing with the state-of-the-art kinship verification methods.

Large-scale {(large-area)}, fine spatial resolution satellite sensor images are valuable data sources for Earth observation while not yet fully exploited by research communities for practical applications. Often, such images exhibit highly complex geometrical structures and spatial patterns, and distinctive characteristics of multiple land-use categories may appear at the same region. Autonomous information extraction from these images is essential in the field of pattern recognition within remote sensing, but this task is extremely challenging due to the spectral and spatial complexity captured in satellite sensor imagery. In this research, a semi-supervised deep rule-based approach for satellite sensor image analysis (SeRBIA) is proposed, where large-scale satellite sensor images are analysed autonomously and classified into detailed land-use categories. Using an ensemble feature descriptor derived from pre-trained AlexNet and VGG-VD-16 models, SeRBIA is capable of learning continuously from both labelled and unlabelled images through self-adaptation without human involvement or intervention. Extensive numerical experiments were conducted on both benchmark datasets and real-world satellite sensor images to comprehensively test the validity and effectiveness of the proposed method. The novel information mining technique developed here can be applied to analyse large-scale satellite sensor images with high accuracy and interpretability, across a wide range of real-world applications.

Representation-based classification (RC) methods such as sparse RC (SRC) have attracted great interest in pattern recognition recently. Despite their empirical success, few theoretical results are reported to justify their effectiveness. In this paper, we establish the theoretical guarantees for a general unified framework termed as atomic representation-based classification (ARC), which includes most RC methods as special cases. We introduce a new condition called atomic classification condition (ACC), which reveals important geometric insights for the theory of ARC. We show that under such condition ARC is provably effective in correctly recognizing any new test sample, even corrupted with noise. Our theoretical analysis significantly broadens the range of conditions under which RC methods succeed for classification in the following two aspects: (1) prior theoretical advances of RC are mainly concerned with the single SRC method while our theory can apply to the general unified ARC framework, including SRC and many other RC methods; and (2) previous works are confined to the analysis of noiseless test data while we provide theoretical guarantees for ARC using both noiseless and noisy test data. Numerical results are provided to validate and complement our theoretical analysis of ARC and its important special cases for both noiseless and noisy test data.

We propose a deep convolutional neural network (CNN) for face detection leveraging on facial attributes based supervision. We observe a phenomenon that part detectors emerge within CNN trained to classify attributes from uncropped face images, without any explicit part supervision. The observation motivates a new method for finding faces through scoring facial parts responses by their spatial structure and arrangement. The scoring mechanism is data-driven, and carefully formulated considering challenging cases where faces are only partially visible. This consideration allows our network to detect faces under severe occlusion and unconstrained pose variations. Our method achieves promising performance on popular benchmarks including FDDB, PASCAL Faces, AFW, and WIDER FACE., Comment: Will appear in TPAMI. arXiv admin note: substantial text overlap with arXiv:1509.06451

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.

The two underlying premises of automatic face recognition are uniqueness and permanence. This paper investigates the permanence property by addressing the following: Does face recognition ability of state-of-the-art systems degrade with elapsed time between enrolled and query face images? If so, what is the rate of decline w.r.t. the elapsed time? While previous studies have reported degradations in accuracy, no formal statistical analysis of large-scale longitudinal data has been conducted. We conduct such an analysis on two mugshot databases, which are the largest facial aging databases studied to date in terms of number of subjects, images per subject, and elapsed times. Mixed-effects regression models are applied to genuine similarity scores from state-of-the-art COTS face matchers to quantify the population-mean rate of change in genuine scores over time, subject-specific variability, and the influence of age, sex, race, and face image quality. Longitudinal analysis shows that despite decreasing genuine scores, 99% of subjects can still be recognized at 0.01% FAR up to approximately 6 years elapsed time, and that age, sex, and race only marginally influence these trends. The methodology presented here should be periodically repeated to determine age-invariant properties of face recognition as state-of-the-art evolves to better address facial aging.

This paper investigates a new annotation technique that reduces significantly the amount of time to annotate training data for gesture recognition. Conventionally, the annotations comprise the start and end times, and the corresponding labels of gestures in sensor recordings. In this work, we propose a one-time point annotation in which labelers do not have to select the start and end time carefully, but just mark a one-time point within the time a gesture is happening. The technique gives more freedom and reduces significantly the burden for labelers. To make the one-time point annotations applicable, we propose a novel BoundarySearch algorithm to find automatically the correct temporal boundaries of gestures by discovering data patterns around their given one-time point annotations. The corrected annotations are then used to train gesture models. We evaluate the method on three applications from wearable gesture recognition with various gesture classes (10-17 classes) recorded with different sensor modalities. The results show that training on the corrected annotations can achieve performances close to a fully supervised training on clean annotations (lower by just up to 5 percent F1-score on average). Furthermore, the BoundarySearch algorithm is also evaluated on the ChaLearn 2014 multi-modal gesture recognition challenge recorded with Kinect sensors from computer vision and achieves similar results.

The advent of cost-effectiveness and easy-operation depth cameras has facilitated a variety of visual recognition tasks including human activity recognition. This paper presents a novel framework for recognizing human activities from video sequences captured by depth cameras. We extend the surface normal to polynormal by assembling local neighboring hypersurface normals from a depth sequence to jointly characterize local motion and shape information. We then propose a general scheme of super normal vector (SNV) to aggregate the low-level polynormals into a discriminative representation, which can be viewed as a simplified version of the Fisher kernel representation. In order to globally capture the spatial layout and temporal order, an adaptive spatio-temporal pyramid is introduced to subdivide a depth video into a set of space-time cells. In the extensive experiments, the proposed approach achieves superior performance to the state-of-the-art methods on the four public benchmark datasets, i.e., MSRAction3D, MSRDailyActivity3D, MSRGesture3D, and MSRActionPairs3D.

Fine-grained recognition concerns categorization at sub-ordinate levels, where the distinction between object classes is highly local. Compared to basic level recognition, fine-grained categorization can be more challenging as there are in general less data and fewer discriminative features. This necessitates the use of a stronger prior for feature selection. In this work, we include humans in the loop to help computers select discriminative features. We introduce a novel online game called "Bubbles" that reveals discriminative features humans use. The player's goal is to identify the category of a heavily blurred image. During the game, the player can choose to reveal full details of circular regions ("bubbles"), with a certain penalty. With proper setup the game generates discriminative bubbles with assured quality. We next propose the "BubbleBank" representation that uses the human selected bubbles to improve machine recognition performance. Finally, we demonstrate how to extend BubbleBank to a view-invariant 3D representation. Experiments demonstrate that our approach yields large improvements over the previous state of the art on challenging benchmarks.

Action prediction is to recognize the class label of an ongoing activity when only a part of it is observed. In this paper, we focus on online action prediction in streaming 3D skeleton sequences. A dilated convolutional network is introduced to model the motion dynamics in temporal dimension via a sliding window over the temporal axis. Since there are significant temporal scale variations in the observed part of the ongoing action at different time steps, a novel window scale selection method is proposed to make our network focus on the performed part of the ongoing action and try to suppress the possible incoming interference from the previous actions at each step. An activation sharing scheme is also proposed to handle the overlapping computations among the adjacent time steps, which enables our framework to run more efficiently. Moreover, to enhance the performance of our framework for action prediction with the skeletal input data, a hierarchy of dilated tree convolutions are also designed to learn the multi-level structured semantic representations over the skeleton joints at each frame. Our proposed approach is evaluated on four challenging datasets. The extensive experiments demonstrate the effectiveness of our method for skeleton-based online action prediction., This paper has been accepted by T-PAMI. DOI: 10.1109/TPAMI.2019.2898954

The goal of transfer learning is to improve the performance of target learning task by leveraging information (or transferring knowledge) from other related tasks. In this paper, we examine the problem of transfer distance metric learning (DML), which usually aims to mitigate the label information deficiency issue in the target DML. Most of the current Transfer DML (TDML) methods are not applicable to the scenario where data are drawn from heterogeneous domains. Some existing heterogeneous transfer learning (HTL) approaches can learn target distance metric by usually transforming the samples of source and target domain into a common subspace. However, these approaches lack flexibility in real-world applications, and the learned transformations are often restricted to be linear. This motivates us to develop a general flexible heterogeneous TDML (HTDML) framework. In particular, any (linear/nonlinear) DML algorithms can be employed to learn the source metric beforehand. Then the pre-learned source metric is represented as a set of knowledge fragments to help target metric learning. We show how generalization error in the target domain could be reduced using the proposed transfer strategy, and develop novel algorithm to learn either linear or nonlinear target metric. Extensive experiments on various applications demonstrate the effectiveness of the proposed method. Ministry of Education (MOE) Accepted version This research was supported in part by Singapore NRF2015ENC-GDCR01001-003, administrated via IMDA, NRF2015ENC-GBICRD001-012, administrated via BCA, DSAIR@NTU, and Australian Research Council Projects FL-170100117, DP-180103424, and DP-140102164.

Linear discriminant analysis (LDA) is a powerful technique in pattern recognition to reduce the dimensionality of data vectors. It maximizes discriminability by retaining only those directions that minimize the ratio of within-class and between-class variance. In this paper, using the same principles as for conventional LDA, we propose to employ uncertainties of the noisy or distorted input data in order to estimate maximally discriminant directions. We demonstrate the efficiency of the proposed uncertain LDA on two applications using state-of-the-art techniques. First, we experiment with an automatic speech recognition task, in which the uncertainty of observations is imposed by real-world additive noise. Next, we examine a full-scale speaker recognition system, considering the utterance duration as the source of uncertainty in authenticating a speaker. The experimental results show that when employing an appropriate uncertainty estimation algorithm, uncertain LDA outperforms its conventional LDA counterpart.

Human detection in dense crowds is an important problem, as it is a prerequisite to many other visual tasks, such as tracking, counting, action recognition or anomaly detection in behaviors exhibited by individuals in a dense crowd. This problem is challenging due to the large number of individuals, small apparent size, severe occlusions and perspective distortion. However, crowded scenes also offer contextual constraints that can be used to tackle these challenges. In this paper, we explore context for human detection in dense crowds in the form of a locally-consistent scale prior which captures the similarity in scale in local neighborhoods and its smooth variation over the image. Using the scale and confidence of detections obtained from an underlying human detector, we infer scale and confidence priors using Markov Random Field. In an iterative mechanism, the confidences of detection hypotheses are modified to reflect consistency with the inferred priors, and the priors are updated based on the new detections. The final set of detections obtained are then reasoned for occlusion using Binary Integer Programming where overlaps and relations between parts of individuals are encoded as linear constraints. Both human detection and occlusion reasoning in proposed approach are solved with local neighbor-dependent constraints, thereby respecting the inter-dependence between individuals characteristic to dense crowd analysis. In addition, we propose a mechanism to detect different combinations of body parts without requiring annotations for individual combinations. We performed experiments on a new and extremely challenging dataset of dense crowd images showing marked improvement over the underlying human detector.

A widely used approach for locating points on deformable objects in images is to generate feature response images for each point, and then to fit a shape model to these response images. We demonstrate that Random Forest regression-voting can be used to generate high quality response images quickly. Rather than using a generative or a discriminative model to evaluate each pixel, a regressor is used to cast votes for the optimal position of each point. We show that this leads to fast and accurate shape model matching when applied in the Constrained Local Model framework. We evaluate the technique in detail, and compare it with a range of commonly used alternatives across application areas: the annotation of the joints of the hands in radiographs and the detection of feature points in facial images. We show that our approach outperforms alternative techniques, achieving what we believe to be the most accurate results yet published for hand joint annotation and state-of-the-art performance for facial feature point detection.

Gait recognition is an important topic in biometrics. Current works primarily focus on recognizing a single person's walking gait. However, a person's gait will change when they walk with other people. How to recognize the gait of multiple people walking is still a challenging problem. This paper proposes an attribute discovery model in a max-margin framework to recognize a person based on gait while walking with multiple people. First, human graphlets are integrated into a tracking-by-detection method to obtain a person's complete silhouette. Then, stable and discriminative attributes are developed using a latent conditional random field (L-CRF) model. The model is trained in the latent structural support vector machine (SVM) framework, in which a new constraint is added to improve the multi-gait recognition performance. In the recognition process, the attribute set of each person is detected by inferring on the trained L-CRF model. Finally, attributes based on dense trajectories are extracted as the final gait features to complete the recognition. The experimental results demonstrate that the proposed method achieves better recognition performance than traditional gait recognition methods under the condition of multiple people walking together.

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.

This paper addresses the problems of word spotting and word recognition on images. In word spotting, the goal is to find all instances of a query word in a dataset of images. In recognition, the goal is to recognize the content of the word image, usually aided by a dictionary or lexicon. We describe an approach in which both word images and text strings are embedded in a common vectorial subspace. This is achieved by a combination of label embedding and attributes learning, and a common subspace regression. In this subspace, images and strings that represent the same word are close together, allowing one to cast recognition and retrieval tasks as a nearest neighbor problem. Contrary to most other existing methods, our representation has a fixed length, is low dimensional, and is very fast to compute and, especially, to compare. We test our approach on four public datasets of both handwritten documents and natural images showing results comparable or better than the state-of-the-art on spotting and recognition tasks.

In this paper we study the problem of finding a support of unknown high-dimensional distributions in the presence of labeling information, called Supervised Novelty Detection (SND). The One-Class Support Vector Machine (SVM) is a widely used kernel-based technique to address this problem. However with the latter approach it is difficult to model a mixture of distributions from which the support might be constituted. We address this issue by presenting a new class of SVM-like algorithms which help to approach multi-class classification and novelty detection from a new perspective. We introduce a new coupling term between classes which leverages the problem of finding a good decision boundary while preserving the compactness of a support with the l2-norm penalty. First we present our optimization objective in the primal and then derive a dual QP formulation of the problem. Next we propose a Least-Squares formulation which results in a linear system which drastically reduces computational costs. Finally we derive a Pegasos-based formulation which can effectively cope with large data sets that cannot be handled by many existing QP solvers. We complete our paper with experiments that validate the usefulness and practical importance of the proposed methods both in classification and novelty detection settings. ispartof: IEEE Transactions on Pattern Analysis and Machine Intelligence vol:36 issue:12 pages:2510-2523 ispartof: location:United States status: published

We address the problem of structure learning of human motion in order to recognize actions from a continuous monocular motion sequence of an arbitrary person from an arbitrary viewpoint. Human motion sequences are represented by multivariate time series in the joint-trajectories space. Under this structured time series framework, we first propose Kernelized Temporal Cut (KTC), an extension of previous works on change-point detection by incorporating Hilbert space embedding of distributions, to handle the nonparametric and high dimensionality issues of human motions. Experimental results demonstrate the effectiveness of our approach, which yields realtime segmentation, and produces high action segmentation accuracy. Second, a spatio-temporal manifold framework is proposed to model the latent structure of time series data. Then an efficient spatio-temporal alignment algorithm Dynamic Manifold Warping (DMW) is proposed for multivariate time series to calculate motion similarity between action sequences (segments). Furthermore, by combining the temporal segmentation algorithm and the alignment algorithm, online human action recognition can be performed by associating a few labeled examples from motion capture data. The results on human motion capture data and 3D depth sensor data demonstrate the effectiveness of the proposed approach in automatically segmenting and recognizing motion sequences, and its ability to handle noisy and partially occluded data, in the transfer learning module.

We introduce a new dataset, Human3.6M, of 3.6 Million accurate 3D Human poses, acquired by recording the performance of 5 female and 6 male subjects, under 4 different viewpoints, for training realistic human sensing systems and for evaluating the next generation of human pose estimation models and algorithms. Besides increasing the size of the datasets in the current state-of-the-art by several orders of magnitude, we also aim to complement such datasets with a diverse set of motions and poses encountered as part of typical human activities (taking photos, talking on the phone, posing, greeting, eating, etc.), with additional synchronized image, human motion capture, and time of flight (depth) data, and with accurate 3D body scans of all the subject actors involved. We also provide controlled mixed reality evaluation scenarios where 3D human models are animated using motion capture and inserted using correct 3D geometry, in complex real environments, viewed with moving cameras, and under occlusion. Finally, we provide a set of large-scale statistical models and detailed evaluation baselines for the dataset illustrating its diversity and the scope for improvement by future work in the research community. Our experiments show that our best large-scale model can leverage our full training set to obtain a 20% improvement in performance compared to a training set of the scale of the largest existing public dataset for this problem. Yet the potential for improvement by leveraging higher capacity, more complex models with our large dataset, is substantially vaster and should stimulate future research. The dataset together with code for the associated large-scale learning models, features, visualization tools, as well as the evaluation server, is available online at http://vision.imar.ro/human3.6m .

We study the problem of object recognition for categories for which we have no training examples, a task also called zero--data or zero-shot learning. This situation has hardly been studied in computer vision research, even though it occurs frequently; the world contains tens of thousands of different object classes, and image collections have been formed and suitably annotated for only a few of them. To tackle the problem, we introduce attribute-based classification: Objects are identified based on a high-level description that is phrased in terms of semantic attributes, such as the object's color or shape. Because the identification of each such property transcends the specific learning task at hand, the attribute classifiers can be prelearned independently, for example, from existing image data sets unrelated to the current task. Afterward, new classes can be detected based on their attribute representation, without the need for a new training phase. In this paper, we also introduce a new data set, Animals with Attributes, of over 30,000 images of 50 animal classes, annotated with 85 semantic attributes. Extensive experiments on this and two more data sets show that attribute-based classification indeed is able to categorize images without access to any training images of the target classes.

This paper presents animated pose templates (APTs) for detecting short-term, long-term, and contextual actions from cluttered scenes in videos. Each pose template consists of two components: 1) a shape template with deformable parts represented in an And-node whose appearances are represented by the Histogram of Oriented Gradient (HOG) features, and 2) a motion template specifying the motion of the parts by the Histogram of Optical-Flows (HOF) features. A shape template may have more than one motion template represented by an Or-node. Therefore, each action is defined as a mixture (Or-node) of pose templates in an And-Or tree structure. While this pose template is suitable for detecting short-term action snippets in two to five frames, we extend it in two ways: 1) For long-term actions, we animate the pose templates by adding temporal constraints in a Hidden Markov Model (HMM), and 2) for contextual actions, we treat contextual objects as additional parts of the pose templates and add constraints that encode spatial correlations between parts. To train the model, we manually annotate part locations on several keyframes of each video and cluster them into pose templates using EM. This leaves the unknown parameters for our learning algorithm in two groups: 1) latent variables for the unannotated frames including pose-IDs and part locations, 2) model parameters shared by all training samples such as weights for HOG and HOF features, canonical part locations of each pose, coefficients penalizing pose-transition and part-deformation. To learn these parameters, we introduce a semi-supervised structural SVM algorithm that iterates between two steps: 1) learning (updating) model parameters using labeled data by solving a structural SVM optimization, and 2) imputing missing variables (i.e., detecting actions on unlabeled frames) with parameters learned from the previous step and progressively accepting high-score frames as newly labeled examples. This algorithm belongs to a family of optimization methods known as the Concave-Convex Procedure (CCCP) that converge to a local optimal solution. The inference algorithm consists of two components: 1) Detecting top candidates for the pose templates, and 2) computing the sequence of pose templates. Both are done by dynamic programming or, more precisely, beam search. In experiments, we demonstrate that this method is capable of discovering salient poses of actions as well as interactions with contextual objects. We test our method on several public action data sets and a challenging outdoor contextual action data set collected by ourselves. The results show that our model achieves comparable or better performance compared to state-of-the-art methods.

Kinship verification from facial images is an interesting and challenging problem in computer vision, and there are very limited attempts on tackle this problem in the literature. In this paper, we propose a new neighborhood repulsed metric learning (NRML) method for kinship verification. Motivated by the fact that interclass samples (without a kinship relation) with higher similarity usually lie in a neighborhood and are more easily misclassified than those with lower similarity, we aim to learn a distance metric under which the intraclass samples (with a kinship relation) are pulled as close as possible and interclass samples lying in a neighborhood are repulsed and pushed away as far as possible, simultaneously, such that more discriminative information can be exploited for verification. To make better use of multiple feature descriptors to extract complementary information, we further propose a multiview NRML (MNRML) method to seek a common distance metric to perform multiple feature fusion to improve the kinship verification performance. Experimental results are presented to demonstrate the efficacy of our proposed methods. Finally, we also test human ability in kinship verification from facial images and our experimental results show that our methods are comparable to that of human observers.

Local feature descriptor is an important module for face recognition and those like Gabor and local binary patterns (LBP) have proven effective face descriptors. Traditionally, the form of such local descriptors is predefined in a handcrafted way. In this paper, we propose a method to learn a discriminant face descriptor (DFD) in a data-driven way. The idea is to learn the most discriminant local features that minimize the difference of the features between images of the same person and maximize that between images from different people. In particular, we propose to enhance the discriminative ability of face representation in three aspects. First, the discriminant image filters are learned. Second, the optimal neighborhood sampling strategy is soft determined. Third, the dominant patterns are statistically constructed. Discriminative learning is incorporated to extract effective and robust features. We further apply the proposed method to the heterogeneous (cross-modality) face recognition problem and learn DFD in a coupled way (coupled DFD or C-DFD) to reduce the gap between features of heterogeneous face images to improve the performance of this challenging problem. Extensive experiments on FERET, CAS-PEAL-R1, LFW, and HFB face databases validate the effectiveness of the proposed DFD learning on both homogeneous and heterogeneous face recognition problems. The DFD improves POEM and LQP by about 4.5 percent on LFW database and the C-DFD enhances the heterogeneous face recognition performance of LBP by over 25 percent.

Traditional biometric recognition systems rely on a single biometric signature for authentication. While the advantage of using multiple sources of information for establishing the identity has been widely recognized, computational models for multimodal biometrics recognition have only recently received attention. We propose a multimodal sparse representation method, which represents the test data by a sparse linear combination of training data, while constraining the observations from different modalities of the test subject to share their sparse representations. Thus, we simultaneously take into account correlations as well as coupling information among biometric modalities. A multimodal quality measure is also proposed to weigh each modality as it gets fused. Furthermore, we also kernelize the algorithm to handle nonlinearity in data. The optimization problem is solved using an efficient alternative direction method. Various experiments show that the proposed method compares favorably with competing fusion-based methods.

We present a new statistical pattern recognition approach for the problem of left ventricle endocardium tracking in ultrasound data. The problem is formulated as a sequential importance resampling algorithm such that the expected segmentation of the current time step is estimated based on the appearance, shape, and motion models that take into account all previous and current images and previous segmentation contours produced by the method. The new appearance and shape models decouple the affine and nonrigid segmentations of the left ventricle to reduce the running time complexity. The proposed motion model combines the systole and diastole motion patterns and an observation distribution built by a deep neural network. The functionality of our approach is evaluated using a dataset of diseased cases containing 16 sequences and another dataset of normal cases comprised of four sequences, where both sets present long axis views of the left ventricle. Using a training set comprised of diseased and healthy cases, we show that our approach produces more accurate results than current state-of-the-art endocardium tracking methods in two test sequences from healthy subjects. Using three test sequences containing different types of cardiopathies, we show that our method correlates well with interuser statistics produced by four cardiologists.

We propose a saliency model termed SIM (saliency by induction mechanisms), which is based on a low-level spatiochromatic model that has successfully predicted chromatic induction phenomena. In so doing, we hypothesize that the low-level visual mechanisms that enhance or suppress image detail are also responsible for making some image regions more salient. Moreover, SIM adds geometrical grouplets to enhance complex low-level features such as corners, and suppress relatively simpler features such as edges. Since our model has been fitted on psychophysical chromatic induction data, it is largely nonparametric. SIM outperforms state-of-the-art methods in predicting eye fixations on two datasets and using two metrics.

There exists an abundance of systems and algorithms for multiple target detection and tracking in video, and many measures for evaluating the quality of their output have been proposed. The contribution of this paper lies in the following: first, it argues that such performance measures should have two fundamental properties--monotonicity and error type differentiability; second, it shows that the recently proposed measures do not have either of these properties and are, thus, less usable; third, it composes a set of simple measures, partly built on common practice, that does have these properties. The informativeness of the proposed set of performance measures is demonstrated through their application on face detection and tracking results.

This paper presents a novel method for performing efficient cost aggregation in stereo matching. The cost aggregation problem is reformulated from the perspective of a histogram, giving us the potential to reduce the complexity of the cost aggregation in stereo matching significantly. Differently from previous methods which have tried to reduce the complexity in terms of the size of an image and a matching window, our approach focuses on reducing the computational redundancy that exists among the search range, caused by a repeated filtering for all the hypotheses. Moreover, we also reduce the complexity of the window-based filtering through an efficient sampling scheme inside the matching window. The tradeoff between accuracy and complexity is extensively investigated by varying the parameters used in the proposed method. Experimental results show that the proposed method provides high-quality disparity maps with low complexity and outperforms existing local methods. This paper also provides new insights into complexity-constrained stereo-matching algorithm design.

This paper proposes a novel representation of articulated human actions and gestures and facial expressions. The main goals of the proposed approach are: 1) to enable recognition using very few examples, i.e., one or k-shot learning, and 2) meaningful organization of unlabeled datasets by unsupervised clustering. Our proposed representation is obtained by automatically discovering high-level subactions or motion primitives, by hierarchical clustering of observed optical flow in four-dimensional, spatial, and motion flow space. The completely unsupervised proposed method, in contrast to state-of-the-art representations like bag of video words, provides a meaningful representation conducive to visual interpretation and textual labeling. Each primitive action depicts an atomic subaction, like directional motion of limb or torso, and is represented by a mixture of four-dimensional Gaussian distributions. For one--shot and k-shot learning, the sequence of primitive labels discovered in a test video are labeled using KL divergence, and can then be represented as a string and matched against similar strings of training videos. The same sequence can also be collapsed into a histogram of primitives or be used to learn a Hidden Markov model to represent classes. We have performed extensive experiments on recognition by one and k-shot learning as well as unsupervised action clustering on six human actions and gesture datasets, a composite dataset, and a database of facial expressions. These experiments confirm the validity and discriminative nature of the proposed representation.

Tracking and identifying players in sports videos filmed with a single pan-tilt-zoom camera has many applications, but it is also a challenging problem. This paper introduces a system that tackles this difficult task. The system possesses the ability to detect and track multiple players, estimates the homography between video frames and the court, and identifies the players. The identification system combines three weak visual cues, and exploits both temporal and mutual exclusion constraints in a Conditional Random Field (CRF). In addition, we propose a novel Linear Programming (LP) Relaxation algorithm for predicting the best player identification in a video clip. In order to reduce the number of labeled training data required to learn the identification system, we make use of weakly supervised learning with the assistance of play-by-play texts. Experiments show promising results in tracking, homography estimation, and identification. Moreover, weakly supervised learning with play-by-play texts greatly reduces the number of labeled training examples required. The identification system can achieve similar accuracies by using merely 200 labels in weakly supervised learning, while a strongly supervised approach needs a least 20,000 labels.

This paper describes novel event-based spatio-temporal features called time-surfaces and how they can be used to create a hierarchical event-based pattern recognition architecture. Unlike existing hierarchical architectures for pattern recognition, the presented model relies on a time oriented approach to extract spatio-temporal features from the asynchronously acquired dynamics of a visual scene. These dynamics are acquired using biologically inspired frameless asynchronous event-driven vision sensors. Similarly to cortical structures, subsequent layers in our hierarchy extract increasingly abstract features using increasingly large spatio-temporal windows. The central concept is to use the rich temporal information provided by events to create contexts in the form of time-surfaces which represent the recent temporal activity within a local spatial neighborhood. We demonstrate that this concept can robustly be used at all stages of an event-based hierarchical model. First layer feature units operate on groups of pixels, while subsequent layer feature units operate on the output of lower level feature units. We report results on a previously published 36 class character recognition task and a four class canonical dynamic card pip task, achieving near 100 percent accuracy on each. We introduce a new seven class moving face recognition task, achieving 79 percent accuracy.This paper describes novel event-based spatio-temporal features called time-surfaces and how they can be used to create a hierarchical event-based pattern recognition architecture. Unlike existing hierarchical architectures for pattern recognition, the presented model relies on a time oriented approach to extract spatio-temporal features from the asynchronously acquired dynamics of a visual scene. These dynamics are acquired using biologically inspired frameless asynchronous event-driven vision sensors. Similarly to cortical structures, subsequent layers in our hierarchy extract increasingly abstract features using increasingly large spatio-temporal windows. The central concept is to use the rich temporal information provided by events to create contexts in the form of time-surfaces which represent the recent temporal activity within a local spatial neighborhood. We demonstrate that this concept can robustly be used at all stages of an event-based hierarchical model. First layer feature units operate on groups of pixels, while subsequent layer feature units operate on the output of lower level feature units. We report results on a previously published 36 class character recognition task and a four class canonical dynamic card pip task, achieving near 100 percent accuracy on each. We introduce a new seven class moving face recognition task, achieving 79 percent accuracy.

Machine learning techniques for computer vision applications like object recognition, scene classification, etc., require a large number of training samples for satisfactory performance. Especially when classification is to be performed over many categories, providing enough training samples for each category is infeasible. This paper describes new ideas in multiclass active learning to deal with the training bottleneck, making it easier to train large multiclass image classification systems. First, we propose a new interaction modality for training which requires only yes-no type binary feedback instead of a precise category label. The modality is especially powerful in the presence of hundreds of categories. For the proposed modality, we develop a Value-of-Information (VOI) algorithm that chooses informative queries while also considering user annotation cost. Second, we propose an active selection measure that works with many categories and is extremely fast to compute. This measure is employed to perform a fast seed search before computing VOI, resulting in an algorithm that scales linearly with dataset size. Third, we use locality sensitive hashing to provide a very fast approximation to active learning, which gives sublinear time scaling, allowing application to very large datasets. The approximation provides up to two orders of magnitude speedups with little loss in accuracy. Thorough empirical evaluation of classification accuracy, noise sensitivity, imbalanced data, and computational performance on a diverse set of image datasets demonstrates the strengths of the proposed algorithms.

Detecting objects in cluttered scenes and estimating articulated human body parts from 2D images are two challenging problems in computer vision. The difficulty is particularly pronounced in activities involving human-object interactions (e.g., playing tennis), where the relevant objects tend to be small or only partially visible and the human body parts are often self-occluded. We observe, however, that objects and human poses can serve as mutual context to each other-recognizing one facilitates the recognition of the other. In this paper, we propose a mutual context model to jointly model objects and human poses in human-object interaction activities. In our approach, object detection provides a strong prior for better human pose estimation, while human pose estimation improves the accuracy of detecting the objects that interact with the human. On a six-class sports data set and a 24-class people interacting with musical instruments data set, we show that our mutual context model outperforms state of the art in detecting very difficult objects and estimating human poses, as well as classifying human-object interaction activities.

Pedestrian detection is a key problem in computer vision, with several applications that have the potential to positively impact quality of life. In recent years, the number of approaches to detecting pedestrians in monocular images has grown steadily. However, multiple data sets and widely varying evaluation protocols are used, making direct comparisons difficult. To address these shortcomings, we perform an extensive evaluation of the state of the art in a unified framework. We make three primary contributions: 1) We put together a large, well-annotated, and realistic monocular pedestrian detection data set and study the statistics of the size, position, and occlusion patterns of pedestrians in urban scenes, 2) we propose a refined per-frame evaluation methodology that allows us to carry out probing and informative comparisons, including measuring performance in relation to scale and occlusion, and 3) we evaluate the performance of sixteen pretrained state-of-the-art detectors across six data sets. Our study allows us to assess the state of the art and provides a framework for gauging future efforts. Our experiments show that despite significant progress, performance still has much room for improvement. In particular, detection is disappointing at low resolutions and for partially occluded pedestrians.

The widespread deployment of Automated Fingerprint Identification Systems (AFIS) in law enforcement and border control applications has heightened the need for ensuring that these systems are not compromised. While several issues related to fingerprint system security have been investigated, including the use of fake fingerprints for masquerading identity, the problem of fingerprint alteration or obfuscation has received very little attention. Fingerprint obfuscation refers to the deliberate alteration of the fingerprint pattern by an individual for the purpose of masking his identity. Several cases of fingerprint obfuscation have been reported in the press. Fingerprint image quality assessment software (e.g., NFIQ) cannot always detect altered fingerprints since the implicit image quality due to alteration may not change significantly. The main contributions of this paper are: 1) compiling case studies of incidents where individuals were found to have altered their fingerprints for circumventing AFIS, 2) investigating the impact of fingerprint alteration on the accuracy of a commercial fingerprint matcher, 3) classifying the alterations into three major categories and suggesting possible countermeasures, 4) developing a technique to automatically detect altered fingerprints based on analyzing orientation field and minutiae distribution, and 5) evaluating the proposed technique and the NFIQ algorithm on a large database of altered fingerprints provided by a law enforcement agency. Experimental results show the feasibility of the proposed approach in detecting altered fingerprints and highlight the need to further pursue this problem.

In many tasks in pattern recognition, such as automatic speech recognition (ASR), optical character recognition (OCR), part-of-speech (POS) tagging, and other string recognition tasks, we are faced with a well-known inconsistency: The Bayes decision rule is usually used to minimize string (symbol sequence) error, whereas, in practice, we want to minimize symbol (word, character, tag, etc.) error. When comparing different recognition systems, we do indeed use symbol error rate as an evaluation measure. The topic of this work is to analyze the relation between string (i.e., 0-1) and symbol error (i.e., metric, integer valued) cost functions in the Bayes decision rule, for which fundamental analytic results are derived. Simple conditions are derived for which the Bayes decision rule with integer-valued metric cost function and with 0-1 cost gives the same decisions or leads to classes with limited cost. The corresponding conditions can be tested with complexity linear in the number of classes. The results obtained do not make any assumption w.r.t. the structure of the underlying distributions or the classification problem. Nevertheless, the general analytic results are analyzed via simulations of string recognition problems with Levenshtein (edit) distance cost function. The results support earlier findings that considerable improvements are to be expected when initial error rates are high.

This paper considers scalable and unobtrusive activity recognition using on-body sensing for context awareness in wearable computing. Common methods for activity recognition rely on supervised learning requiring substantial amounts of labeled training data. Obtaining accurate and detailed annotations of activities is challenging, preventing the applicability of these approaches in real-world settings. This paper proposes new annotation strategies that substantially reduce the required amount of annotation. We explore two learning schemes for activity recognition that effectively leverage such sparsely labeled data together with more easily obtainable unlabeled data. Experimental results on two public data sets indicate that both approaches obtain results close to fully supervised techniques. The proposed methods are robust to the presence of erroneous labels occurring in real-world annotation data.

In this paper, we define meta-recognition, a performance prediction method for recognition algorithms, and examine the theoretical basis for its postrecognition score analysis form through the use of the statistical extreme value theory (EVT). The ability to predict the performance of a recognition system based on its outputs for each match instance is desirable for a number of important reasons, including automatic threshold selection for determining matches and nonmatches, and automatic algorithm selection or weighting for multi-algorithm fusion. The emerging body of literature on postrecognition score analysis has been largely constrained to biometrics, where the analysis has been shown to successfully complement or replace image quality metrics as a predictor. We develop a new statistical predictor based upon the Weibull distribution, which produces accurate results on a per instance recognition basis across different recognition problems. Experimental results are provided for two different face recognition algorithms, a fingerprint recognition algorithm, a SIFT-based object recognition system, and a content-based image retrieval system.

A new condition for high accuracy on test sets is given for the method of stochastic discrimination (SD), a pattern recognition method introduced by Kleinberg. This condition provides a simple explanation for the observed good generalization properties and overtraining-resistance. We also show that the method of SD remains valid if the original assumption of uniform distribution on a finite space for resampling is relaxed.

Detecting vehicles in aerial images has a wide range of applications, from urban planning to visual surveillance. We describe a vehicle detector that improves upon previous approaches by incorporating a very large and rich set of image descriptors. A new feature set called Color Probability Maps is used to capture the color statistics of vehicles and their surroundings, along with the Histograms of Oriented Gradients feature and a simple yet powerful image descriptor that captures the structural characteristics of objects named Pairs of Pixels. The combination of these features leads to an extremely high-dimensional feature set (approximately 70,000 elements). Partial Least Squares is first used to project the data onto a much lower dimensional sub-space. Then, a powerful feature selection analysis is employed to improve the performance while vastly reducing the number of features that must be calculated. We compare our system to previous approaches on two challenging data sets and show superior performance.

Selecting features for multiclass classification is a critically important task for pattern recognition and machine learning applications. Especially challenging is selecting an optimal subset of features from high-dimensional data, which typically have many more variables than observations and contain significant noise, missing components, or outliers. Existing methods either cannot handle high-dimensional data efficiently or scalably, or can only obtain local optimum instead of global optimum. Toward the selection of the globally optimal subset of features efficiently, we introduce a new selector - which we call the Fisher-Markov selector - to identify those features that are the most useful in describing essential differences among the possible groups. In particular, in this paper we present a way to represent essential discriminating characteristics together with the sparsity as an optimization objective. With properly identified measures for the sparseness and discriminativeness in possibly high-dimensional settings, we take a systematic approach for optimizing the measures to choose the best feature subset. We use Markov random field optimization techniques to solve the formulated objective functions for simultaneous feature selection. Our results are noncombinatorial, and they can achieve the exact global optimum of the objective function for some special kernels. The method is fast; in particular, it can be linear in the number of features and quadratic in the number of observations. We apply our procedure to a variety of real-world data, including mid--dimensional optical handwritten digit data set and high-dimensional microarray gene expression data sets. The effectiveness of our method is confirmed by experimental results. In pattern recognition and from a model selection viewpoint, our procedure says that it is possible to select the most discriminating subset of variables by solving a very simple unconstrained objective function which in fact can be obtained with an explicit expression.

We consider the problem of spatially and temporally registering multiple video sequences of dynamical scenes which contain, but are not limited to, nonrigid objects such as fireworks, flags fluttering in the wind, etc., taken from different vantage points. This problem is extremely challenging due to the presence of complex variations in the appearance of such dynamic scenes. In this paper, we propose a simple algorithm for matching such complex scenes. Our algorithm does not require the cameras to be synchronized, and is not based on frame-by-frame or volume-by-volume registration. Instead, we model each video as the output of a linear dynamical system and transform the task of registering the video sequences to that of registering the parameters of the corresponding dynamical models. As these parameters are not uniquely defined, one cannot directly compare them to perform registration. We resolve these ambiguities by jointly identifying the parameters from multiple video sequences, and converting the identified parameters to a canonical form. This reduces the video registration problem to a multiple image registration problem, which can be efficiently solved using existing image matching techniques. We test our algorithm on a wide variety of challenging video sequences and show that it matches the performance of significantly more computationally expensive existing methods.

A variety of different scripts are used in writing languages throughout the world. In a multiscript, multilingual environment, it is essential to know the script used in writing a document before an appropriate character recognition and document analysis algorithm can be chosen. In view of this, several methods for automatic script identification have been developed so far. They mainly belong to two broad categories-structure-based and visual-appearance-based techniques. This survey report gives an overview of the different script identification methodologies under each of these categories. Methods for script identification in online data and video-texts are also presented. It is noted that the research in this field is relatively thin and still more research is to be done, particularly in the case of handwritten documents.

Human age, as an important personal trait, can be directly inferred by distinct patterns emerging from the facial appearance. Derived from rapid advances in computer graphics and machine vision, computer-based age synthesis and estimation via faces have become particularly prevalent topics recently because of their explosively emerging real-world applications, such as forensic art, electronic customer relationship management, security control and surveillance monitoring, biometrics, entertainment, and cosmetology. Age synthesis is defined to rerender a face image aesthetically with natural aging and rejuvenating effects on the individual face. Age estimation is defined to label a face image automatically with the exact age (year) or the age group (year range) of the individual face. Because of their particularity and complexity, both problems are attractive yet challenging to computer-based application system designers. Large efforts from both academia and industry have been devoted in the last a few decades. In this paper, we survey the complete state-of-the-art techniques in the face image-based age synthesis and estimation topics. Existing models, popular algorithms, system performances, technical difficulties, popular face aging databases, evaluation protocols, and promising future directions are also provided with systematic discussions.

Linear filters are ubiquitously used as a preprocessing step for many classification tasks in computer vision. In particular, applying Gabor filters followed by a classification stage, such as a support vector machine (SVM), is now common practice in computer vision applications like face identity and expression recognition. A fundamental problem occurs, however, with respect to the high dimensionality of the concatenated Gabor filter responses in terms of memory requirements and computational efficiency during training and testing. In this paper, we demonstrate how the preprocessing step of applying a bank of linear filters can be reinterpreted as manipulating the type of margin being maximized within the linear SVM. This new interpretation leads to sizable memory and computational advantages with respect to existing approaches. The reinterpreted formulation turns out to be independent of the number of filters, thereby allowing the examination of the feature spaces derived from arbitrarily large number of linear filters, a hitherto untestable prospect. Further, this new interpretation of filter banks gives new insights, other than the often cited biological motivations, into why the preprocessing of images with filter banks, like Gabor filters, improves classification performance.