Search

Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion. To overcome this challenge, one recent work builds an action-click supervision framework. It requires similar annotation costs but can steadily improve the localization performance when compared to the conventional weakly supervised methods. In this paper, by revealing that the performance bottleneck of the existing approaches mainly comes from the background errors, we find that a stronger action localizer can be trained with labels on the background video frames rather than those on the action frames. To this end, we convert the action-click supervision to the background-click supervision and develop a novel method, called BackTAL. Specifically, BackTAL implements two-fold modeling on the background video frames, i.e., the position modeling and the feature modeling. In position modeling, we not only conduct supervised learning on the annotated video frames but also design a score separation module to enlarge the score differences between the potential action frames and backgrounds. In feature modeling, we propose an affinity module to measure frame-specific similarities among neighboring frames and dynamically attend to informative neighbors when calculating temporal convolution. Extensive experiments on three benchmarks are conducted, which demonstrate the high performance of the established BackTAL and the rationality of the proposed background-click supervision. [ABSTRACT FROM AUTHOR]

The goal of this work is to recognise phrases and sentences being spoken by a talking face, with or without the audio. Unlike previous works that have focussed on recognising a limited number of words or phrases, we tackle lip reading as an open-world problem – unconstrained natural language sentences, and in the wild videos. Our key contributions are: (1) we compare two models for lip reading, one using a CTC loss, and the other using a sequence-to-sequence loss. Both models are built on top of the transformer self-attention architecture; (2) we investigate to what extent lip reading is complementary to audio speech recognition, especially when the audio signal is noisy; (3) we introduce and publicly release a new dataset for audio-visual speech recognition, LRS2-BBC, consisting of thousands of natural sentences from British television. The models that we train surpass the performance of all previous work on a lip reading benchmark dataset by a significant margin. [ABSTRACT FROM AUTHOR]

When viewing omnidirectional images (ODIs), viewers can access different viewports via head movement (HM), which sequentially forms head trajectories in spatial-temporal domain. Thus, head trajectories play a key role in modeling human attention on ODIs. In this paper, we establish a large-scale dataset collecting 21,600 head trajectories on 1,080 ODIs. By mining our dataset, we find two important factors influencing head trajectories, i.e., temporal dependency and subject-specific variance. Accordingly, we propose a novel approach integrating hierarchical Bayesian inference into long short-term memory (LSTM) network for head trajectory prediction on ODIs, which is called HiBayes-LSTM. In HiBayes-LSTM, we develop a mechanism of Future Intention Estimation (FIE), which captures the temporal correlations from previous, current and estimated future information, for predicting viewport transition. Additionally, a training scheme called Hierarchical Bayesian inference (HBI) is developed for modeling inter-subject uncertainty in HiBayes-LSTM. For HBI, we introduce a joint Gaussian distribution in a hierarchy, to approximate the posterior distribution over network weights. By sampling subject-specific weights from the approximated posterior distribution, our HiBayes-LSTM approach can yield diverse viewport transition among different subjects and obtain multiple head trajectories. Extensive experiments validate that our HiBayes-LSTM approach significantly outperforms 9 state-of-the-art approaches for trajectory prediction on ODIs, and then it is successfully applied to predict saliency on ODIs. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel deep Efficient Relational Sentence Ordering Network (referred to as ERSON) by leveraging pre-trained language model in both encoder and decoder architectures to strengthen the coherence modeling of the entire model. Specifically, we first introduce a divide-and-fuse BERT (referred to as DF-BERT), a new refactor of BERT network, where lower layers in the improved model encode each sentence in the paragraph independently, which are shared by different sentence pairs, and the higher layers learn the cross-attention between sentence pairs jointly. It enables us to capture the semantic concepts and contextual information between the sentences of the paragraph, while significantly reducing the runtime and memory consumption without sacrificing the model performance. Besides, a Relational Pointer Decoder (referred to as RPD) is developed, which utilizes the pre-trained Next Sentence Prediction (NSP) task of BERT to capture the useful relative ordering information between sentences to enhance the order predictions. In addition, a variety of knowledge distillation based losses are added as auxiliary supervision to further improve the ordering performance. The extensive evaluations on Sentence Ordering, Order Discrimination, and Multi-Document Summarization tasks show the superiority of ERSON to the state-of-the-art ordering methods. [ABSTRACT FROM AUTHOR]

In a real life process evolving over time, the relationship between its relevant variables may change. Therefore, it is advantageous to have different inference models for each state of the process. Asymmetric hidden Markov models fulfil this dynamical requirement and provide a framework where the trend of the process can be expressed as a latent variable. In this paper, we modify these recent asymmetric hidden Markov models to have an asymmetric autoregressive component in the case of continuous variables, allowing the model to choose the order of autoregression that maximizes its penalized likelihood for a given training set. Additionally, we show how inference, hidden states decoding and parameter learning must be adapted to fit the proposed model. Finally, we run experiments with synthetic and real data to show the capabilities of this new model. [ABSTRACT FROM AUTHOR]

Despite the remarkable progress achieved in conventional instance segmentation, the problem of predicting instance segmentation results for unobserved future frames remains challenging due to the unobservability of future data. Existing methods mainly address this challenge by forecasting features of future frames. However, these methods always treat features of multiple levels (e.g., coarse-to-fine pyramid features) independently and do not exploit them collaboratively, which results in inaccurate prediction for future frames; and moreover, such a weakness can partially hinder self-adaption of a future segmentation prediction model for different input samples. To solve this problem, we propose an adaptive aggregation approach called Auto-Path Aggregation Network (APANet), where the spatio-temporal contextual information obtained in the features of each individual level is selectively aggregated using the developed “auto-path”. The “auto-path” connects each pair of features extracted at different pyramid levels for task-specific hierarchical contextual information aggregation, which enables selective and adaptive aggregation of pyramid features in accordance with different videos/frames. Our APANet can be further optimized jointly with the Mask R-CNN head as a feature decoder and a Feature Pyramid Network (FPN) feature encoder, forming a joint learning system for future instance segmentation prediction. We experimentally show that the proposed method can achieve state-of-the-art performance on three video-based instance segmentation benchmarks for future instance segmentation prediction. [ABSTRACT FROM AUTHOR]

Supervised dimensionality reduction for sequence data learns a transformation that maps the observations in sequences onto a low-dimensional subspace by maximizing the separability of sequences in different classes. It is typically more challenging than conventional dimensionality reduction for static data, because measuring the separability of sequences involves non-linear procedures to manipulate the temporal structures. In this paper, we propose a linear method, called order-preserving Wasserstein discriminant analysis (OWDA), and its deep extension, namely DeepOWDA, to learn linear and non-linear discriminative subspace for sequence data, respectively. We construct novel separability measures between sequence classes based on the order-preserving Wasserstein (OPW) distance to capture the essential differences among their temporal structures. Specifically, for each class, we extract the OPW barycenter and construct the intra-class scatter as the dispersion of the training sequences around the barycenter. The inter-class distance is measured as the OPW distance between the corresponding barycenters. We learn the linear and non-linear transformations by maximizing the inter-class distance and minimizing the intra-class scatter. In this way, the proposed OWDA and DeepOWDA are able to concentrate on the distinctive differences among classes by lifting the geometric relations with temporal constraints. Experiments on four 3D action recognition datasets show the effectiveness of OWDA and DeepOWDA. [ABSTRACT FROM AUTHOR]

We propose a ParametRIc MAnifold Learning (PRIMAL) algorithm for Gaussian mixtures models (GMM), assuming that GMMs lie on or near to a manifold of probability distributions that is generated from a low-dimensional hierarchical latent space through parametric mappings. Inspired by principal component analysis (PCA), the generative processes for priors, means and covariance matrices are modeled by their respective latent space and parametric mapping. Then, the dependencies between latent spaces are captured by a hierarchical latent space by a linear or kernelized mapping. The function parameters and hierarchical latent space are learned by minimizing the reconstruction error between ground-truth GMMs and manifold-generated GMMs, measured by Kullback-Leibler Divergence (KLD). Variational approximation is employed to handle the intractable KLD between GMMs and a variational EM algorithm is derived to optimize the objective function. Experiments on synthetic data, flow cytometry analysis, eye-fixation analysis and topic models show that PRIMAL learns a continuous and interpretable manifold of GMM distributions and achieves a minimum reconstruction error. [ABSTRACT FROM AUTHOR]

Detection, parsing, and future predictions on sequence data (e.g., videos) require the algorithms to capture non-Markovian and compositional properties of high-level semantics. Context-free grammars are natural choices to capture such properties, but traditional grammar parsers (e.g., Earley parser) only take symbolic sentences as inputs. In this paper, we generalize the Earley parser to parse sequence data which is neither segmented nor labeled. Given the output of an arbitrary probabilistic classifier, this generalized Earley parser finds the optimal segmentation and labels in the language defined by the input grammar. Based on the parsing results, it makes top-down future predictions. The proposed method is generic, principled, and widely applicable. Experiment results clearly show the benefit of our method for both human activity parsing and prediction on three video datasets. [ABSTRACT FROM AUTHOR]

We begin by reiterating that common neural network activation functions have simple Bayesian origins. In this spirit, we go on to show that Bayes's theorem also implies a simple recurrence relation; this leads to a Bayesian recurrent unit with a prescribed feedback formulation. We show that introduction of a context indicator leads to a variable feedback that is similar to the forget mechanism in conventional recurrent units. A similar approach leads to a probabilistic input gate. The Bayesian formulation leads naturally to the two pass algorithm of the Kalman smoother or forward-backward algorithm, meaning that inference naturally depends upon future inputs as well as past ones. Experiments on speech recognition confirm that the resulting architecture can perform as well as a bidirectional recurrent network with the same number of parameters as a unidirectional one. Further, when configured explicitly bidirectionally, the architecture can exceed the performance of a conventional bidirectional recurrence. [ABSTRACT FROM AUTHOR]

Smart homes equipped with anonymous binary sensors offer a low-cost, unobtrusive solution that powers activity-aware applications, such as building automation, health monitoring, behavioral intervention, and home security. However, when multiple residents are living in a smart home, associating sensor events with the corresponding residents can pose a major challenge. Previous approaches to multi-resident tracking in smart homes rely on extra information, such as sensor layouts, floor plans, and annotated data, which may not be available or inconvenient to obtain in practice. To address those challenges in real-life deployment, we introduce the sMRT algorithm that simultaneously tracks the location of each resident and estimates the number of residents in the smart home, without relying on ground-truth annotated sensor data or other additional information. We evaluate the performance of our approach using two smart home datasets recorded in real-life settings and compare sMRT with two other methods that rely on sensor layout and ground truth-labeled sensor data. [ABSTRACT FROM AUTHOR]

A visual scanpath represents the human eye movements when scanning the visual field for acquiring and receiving visual information. Predicting visual scanpaths when a certain stimulus is presented plays an important role in modeling overt human visual attention and search behavior. In this paper, we presented an ’Inhibition of Return - Region of Interest’ (IOR-ROI) recurrent mixture density network based framework learning to produce human-like visual scanpaths under task-free viewing conditions. The proposed model simultaneously predicts a sequence of ordered fixation positions and their corresponding fixation durations. Our model integrates bottom-up features and semantic features extracted by convolutional neural networks. Then the integrated feature maps are fed into the IOR-ROI Long Short-Term Memory (LSTM) which is the core component of the proposed model. The IOR-ROI LSTM is a dual LSTM unit, i.e., the IOR-LSTM and the ROI-LSTM, capturing IOR dynamics and gaze shift behavior simultaneously. IOR-LSTM simulates the visual working memory to adaptively maintain and update visual information regarding previously fixated regions. ROI-LSTM is responsible for predicting the next possible ROIs given the spatially inhibited image feature maps on the feature-wise basis. Fixation duration is predicted by a regression neural network given the viewing history and image feature maps corresponding to currently fixated ROI. Considering the eye movement pattern variations among subjects, a mixture density network is adopted to model the next fixation distribution as Gaussian mixtures and the fixation duration is also modeled using Gaussian distribution. Our model is evaluated on the OSIE and MIT low resolution eye-tracking datasets and experimental results indicate that the proposed method can achieve superior performance in predicting visual scanpaths. The code will be publicly available on URL: https://github.com/sunwj/scanpath . [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel unsupervised approach for sequence matching by explicitly accounting for the locality properties in the sequences. In contrast to conventional approaches that rely on frame-to-frame matching, we conduct matching using sequencelet or seqlet, a sub-sequence wherein the frames share strong similarities and are thus grouped together. The optimal seqlets and matching between them are learned jointly, without any supervision from users. The learned seqlets preserve the locality information at the scale of interest and resolve the ambiguities during matching, which are omitted by frame-based matching methods. We show that our proposed approach outperforms the state-of-the-art ones on datasets of different domains including human actions, facial expressions, speech, and character strokes. [ABSTRACT FROM AUTHOR]

Low-dimensional discriminative representations enhance machine learning methods in both performance and complexity. This has motivated supervised dimensionality reduction (DR), which transforms high-dimensional data into a discriminative subspace. Most DR methods require data to be i.i.d. However, in some domains, data naturally appear in sequences, where the observations are temporally correlated. We propose a DR method, namely, latent temporal linear discriminant analysis (LT-LDA), to learn low-dimensional temporal representations. We construct the separability among sequence classes by lifting the holistic temporal structures, which are established based on temporal alignments and may change in different subspaces. We jointly learn the subspace and the associated latent alignments by optimizing an objective that favors easily separable temporal structures. We show that this objective is connected to the inference of alignments and thus allows for an iterative solution. We provide both theoretical insight and empirical evaluations on several real-world sequence datasets to show the applicability of our method. [ABSTRACT FROM AUTHOR]

Facial expression analysis could be greatly improved by incorporating spatial and temporal patterns present in facial behavior, but the patterns have not yet been utilized to their full advantage. We remedy this via a novel dynamic model-an interval temporal restricted Boltzmann machine (IT-RBM) - that is able to capture both universal spatial patterns and complicated temporal patterns in facial behavior for facial expression analysis. We regard a facial expression as a multifarious activity composed of sequential or overlapping primitive facial events. Allen's interval algebra is implemented to portray these complicated temporal patterns via a two-layer Bayesian network. The nodes in the upper-most layer are representative of the primitive facial events, and the nodes in the lower layer depict the temporal relationships between those events. Our model also captures inherent universal spatial patterns via a multi-value restricted Boltzmann machine in which the visible nodes are facial events, and the connections between hidden and visible nodes model intrinsic spatial patterns. Efficient learning and inference algorithms are proposed. Experiments on posed and spontaneous expression distinction and expression recognition demonstrate that our proposed IT-RBM achieves superior performance compared to state-of-the art research due to its ability to incorporate these facial behavior patterns. [ABSTRACT FROM AUTHOR]

In this work we present a new approach to the field of weakly supervised learning in the video domain. Our method is relevant to sequence learning problems which can be split up into sub-problems that occur in parallel. Here, we experiment with sign language data. The approach exploits sequence constraints within each independent stream and combines them by explicitly imposing synchronisation points to make use of parallelism that all sub-problems share. We do this with multi-stream HMMs while adding intermediate synchronisation constraints among the streams. We embed powerful CNN-LSTM models in each HMM stream following the hybrid approach. This allows the discovery of attributes which on their own lack sufficient discriminative power to be identified. We apply the approach to the domain of sign language recognition exploiting the sequential parallelism to learn sign language, mouth shape and hand shape classifiers. We evaluate the classifiers on three publicly available benchmark data sets featuring challenging real-life sign language with over 1,000 classes, full sentence based lip-reading and articulated hand shape recognition on a fine-grained hand shape taxonomy featuring over 60 different hand shapes. We clearly outperform the state-of-the-art on all data sets and observe significantly faster convergence using the parallel alignment approach. [ABSTRACT FROM AUTHOR]

We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being Gaussian. For such HMMs, the marginal distribution at any time position follows a Gaussian mixture distribution, a fact exploited to softly match, aka register, the states in two HMMs. We refer to such HMMs as HMM. The registration of states is inspired by the intrinsic relationship of optimal transport and the Wasserstein metric between distributions. Specifically, the components of the marginal GMMs are matched by solving an optimal transport problem where the cost between components is the Wasserstein metric for Gaussian distributions. The solution of the optimization problem is a fast approximation to the Wasserstein metric between two GMMs. The new Aggregated Wasserstein distance is a semi-metric and can be computed without generating Monte Carlo samples. It is invariant to relabeling or permutation of states. The distance is defined meaningfully even for two HMMs that are estimated from data of different dimensionality, a situation that can arise due to missing variables. This distance quantifies the dissimilarity of HMMs by measuring both the difference between the two marginal GMMs and that between the two transition matrices. Our new distance is tested on tasks of retrieval, classification, and t-SNE visualization of time series. Experiments on both synthetic and real data have demonstrated its advantages in terms of accuracy as well as efficiency in comparison with existing distances based on the Kullback-Leibler divergence. [ABSTRACT FROM AUTHOR]

Visual data such as images and videos contain a rich source of structured semantic labels as well as a wide range of interacting components. Visual content could be assigned with fine-grained labels describing major components, coarse-grained labels depicting high level abstractions, or a set of labels revealing attributes. Such categorization over different, interacting layers of labels evinces the potential for a graph-based encoding of label information. In this paper, we exploit this rich structure for performing graph-based inference in label space for a number of tasks: multi-label image and video classification and action detection in untrimmed videos. We consider the use of the Bidirectional Inference Neural Network (BINN) and Structured Inference Neural Network (SINN) for performing graph-based inference in label space and propose a Long Short-Term Memory (LSTM) based extension for exploiting activity progression on untrimmed videos. The methods were evaluated on (i) the Animal with Attributes (AwA), Scene Understanding (SUN) and NUS-WIDE datasets for multi-label image classification, (ii) the first two releases of the YouTube-8M large scale dataset for multi-label video classification, and (iii) the THUMOS'14 and MultiTHUMOS video datasets for action detection. Our results demonstrate the effectiveness of structured label inference in these challenging tasks, achieving significant improvements against baselines. [ABSTRACT FROM AUTHOR]

Action recognition has become a rapidly developing research field within the last decade. But with the increasing demand for large scale data, the need of hand annotated data for the training becomes more and more impractical. One way to avoid frame-based human annotation is the use of action order information to learn the respective action classes. In this context, we propose a hierarchical approach to address the problem of weakly supervised learning of human actions from ordered action labels by structuring recognition in a coarse-to-fine manner. Given a set of videos and an ordered list of the occurring actions, the task is to infer start and end frames of the related action classes within the video and to train the respective action classifiers without any need for hand labeled frame boundaries. We address this problem by combining a framewise RNN model with a coarse probabilistic inference. This combination allows for the temporal alignment of long sequences and thus, for an iterative training of both elements. While this system alone already generates good results, we show that the performance can be further improved by approximating the number of subactions to the characteristics of the different action classes as well as by the introduction of a regularizing length prior. The proposed system is evaluated on two benchmark datasets, the Breakfast and the Hollywood extended dataset, showing a competitive performance on various weak learning tasks such as temporal action segmentation and action alignment. [ABSTRACT FROM AUTHOR]

Panoramic video provides immersive and interactive experience by enabling humans to control the field of view (FoV) through head movement (HM). Thus, HM plays a key role in modeling human attention on panoramic video. This paper establishes a database collecting subjects' HM in panoramic video sequences. From this database, we find that the HM data are highly consistent across subjects. Furthermore, we find that deep reinforcement learning (DRL) can be applied to predict HM positions, via maximizing the reward of imitating human HM scanpaths through the agent's actions. Based on our findings, we propose a DRL-based HM prediction (DHP) approach with offline and online versions, called offline-DHP and online-DHP. In offline-DHP, multiple DRL workflows are run to determine potential HM positions at each panoramic frame. Then, a heat map of the potential HM positions, named the HM map, is generated as the output of offline-DHP. In online-DHP, the next HM position of one subject is estimated given the currently observed HM position, which is achieved by developing a DRL algorithm upon the learned offline-DHP model. Finally, the experiments validate that our approach is effective in both offline and online prediction of HM positions for panoramic video, and that the learned offline-DHP model can improve the performance of online-DHP. [ABSTRACT FROM AUTHOR]

Many modern unsupervised or semi-supervised machine learning algorithms rely on Bayesian probabilistic models. These models are usually intractable and thus require approximate inference. Variational inference (VI) lets us approximate a high-dimensional Bayesian posterior with a simpler variational distribution by solving an optimization problem. This approach has been successfully applied to various models and large-scale applications. In this review, we give an overview of recent trends in variational inference. We first introduce standard mean field variational inference, then review recent advances focusing on the following aspects: (a) scalable VI, which includes stochastic approximations, (b) generic VI, which extends the applicability of VI to a large class of otherwise intractable models, such as non-conjugate models, (c) accurate VI, which includes variational models beyond the mean field approximation or with atypical divergences, and (d) amortized VI, which implements the inference over local latent variables with inference networks. Finally, we provide a summary of promising future research directions. [ABSTRACT FROM AUTHOR]

In this article, a method for segmentation-based learning-free Query by Example (QbE) keyword spotting on handwritten documents is proposed. The method consists of three steps, namely preprocessing, feature extraction and matching, which address critical variations of text images (e.g., skew, translation, different writing styles). During the feature extraction step, a sequence of descriptors is generated using a combination of a zoning scheme and a novel appearance descriptor, referred as modified Projections of Oriented Gradients. The preprocessing step, which includes contrast normalization and main-zone detection, aims to overcome the shortcomings of the appearance descriptor. Moreover, an uneven zoning scheme is introduced by applying a denser zoning only on query images for a more detailed representation. This leads to a significant reduction in storage requirements of a document collection. The distance between the query and word sequences is efficiently computed by the proposed Selective Matching algorithm. This algorithm is further extended to handle an augmented set of images originating from a single query image. The efficiency of the proposed method is demonstrated by experimentation conducted on seven publicly available datasets. In these experiments, the proposed method significantly outperforms all state-of-the-art learning-free techniques. [ABSTRACT FROM AUTHOR]

Human footsteps can provide a unique behavioural pattern for robust biometric systems. We propose spatio-temporal footstep representations from floor-only sensor data in advanced computational models for automatic biometric verification. Our models deliver an artificial intelligence capable of effectively differentiating the fine-grained variability of footsteps between legitimate users (clients) and impostor users of the biometric system. The methodology is validated in the largest to date footstep database, containing nearly 20,000 footstep signals from more than 120 users. The database is organized by considering a large cohort of impostors and a small set of clients to verify the reliability of biometric systems. We provide experimental results in 3 critical data-driven security scenarios, according to the amount of footstep data made available for model training: at airports security checkpoints (smallest training set), workspace environments (medium training set) and home environments (largest training set). We report state-of-the-art footstep recognition rates with an optimal equal false acceptance and false rejection rate (equal error rate) of 0.7 percent an improvement ratio of 371 percent compared to previous state-of-the-art. We perform a feature analysis of deep residual neural networks showing effective clustering of client's footstep data and to provide insights of the feature learning process. [ABSTRACT FROM AUTHOR]

Our experience of the world is multimodal - we see objects, hear sounds, feel texture, smell odors, and taste flavors. Modality refers to the way in which something happens or is experienced and a research problem is characterized as multimodal when it includes multiple such modalities. In order for Artificial Intelligence to make progress in understanding the world around us, it needs to be able to interpret such multimodal signals together. Multimodal machine learning aims to build models that can process and relate information from multiple modalities. It is a vibrant multi-disciplinary field of increasing importance and with extraordinary potential. Instead of focusing on specific multimodal applications, this paper surveys the recent advances in multimodal machine learning itself and presents them in a common taxonomy. We go beyond the typical early and late fusion categorization and identify broader challenges that are faced by multimodal machine learning, namely: representation, translation, alignment, fusion, and co-learning. This new taxonomy will enable researchers to better understand the state of the field and identify directions for future research. [ABSTRACT FROM AUTHOR]

Skeleton-based human action recognition has attracted a lot of research attention during the past few years. Recent works attempted to utilize recurrent neural networks to model the temporal dependencies between the 3D positional configurations of human body joints for better analysis of human activities in the skeletal data. The proposed work extends this idea to spatial domain as well as temporal domain to better analyze the hidden sources of action-related information within the human skeleton sequences in both of these domains simultaneously. Based on the pictorial structure of Kinect's skeletal data, an effective tree-structure based traversal framework is also proposed. In order to deal with the noise in the skeletal data, a new gating mechanism within LSTM module is introduced, with which the network can learn the reliability of the sequential data and accordingly adjust the effect of the input data on the updating procedure of the long-term context representation stored in the unit's memory cell. Moreover, we introduce a novel multi-modal feature fusion strategy within the LSTM unit in this paper. The comprehensive experimental results on seven challenging benchmark datasets for human action recognition demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, a new nonparametric Bayesian model called the dual sticky hierarchical Dirichlet process hidden Markov model (HDP-HMM) is proposed for mining activities from a collection of time series data such as trajectories. All the time series data are clustered. Each cluster of time series data, corresponding to a motion pattern, is modeled by an HMM. Our model postulates a set of HMMs that share a common set of states (topics in an analogy with topic models for document processing), but have unique transition distributions. The number of HMMs and the number of topics are both automatically determined. The sticky prior avoids redundant states and makes our HDP-HMM more effective to model multimodal observations. For the application to motion trajectory modeling, topics correspond to motion activities. The learnt topics are clustered into atomic activities which are assigned predicates. We propose a Bayesian inference method to decompose a given trajectory into a sequence of atomic activities. The sources and sinks in the scene are learnt by clustering endpoints (origins and destinations) of trajectories. The semantic motion regions are learnt using the points in trajectories. On combining the learnt sources and sinks, the learnt semantic motion regions, and the learnt sequence of atomic activities, the action represented by a trajectory can be described in natural language in as automatic a way as possible. The effectiveness of our dual sticky HDP-HMM is validated on several trajectory datasets. The effectiveness of the natural language descriptions for motions is demonstrated on the vehicle trajectories extracted from a traffic scene. [ABSTRACT FROM AUTHOR]

We address the problem of video classification for facial analysis and human action recognition. We propose a novel weakly supervised learning method that models the video as a sequence of automatically mined, discriminative sub-events (e.g., onset and offset phase for “smile”, running and jumping for “highjump”). The proposed model is inspired by the recent works on Multiple Instance Learning and latent SVM/HCRF - it extends such frameworks to model the ordinal aspect in the videos, approximately. We obtain consistent improvements over relevant competitive baselines on four challenging and publicly available video based facial analysis datasets for prediction of expression, clinical pain and intent in dyadic conversations, and on three challenging human action datasets. We also validate the method with qualitative results and show that they largely support the intuitions behind the method. [ABSTRACT FROM AUTHOR]

Online handwritten Chinese text recognition (OHCTR) is a challenging problem as it involves a large-scale character set, ambiguous segmentation, and variable-length input sequences. In this paper, we exploit the outstanding capability of path signature to translate online pen-tip trajectories into informative signature feature maps, successfully capturing the analytic and geometric properties of pen strokes with strong local invariance and robustness. A multi-spatial-context fully convolutional recurrent network (MC-FCRN) is proposed to exploit the multiple spatial contexts from the signature feature maps and generate a prediction sequence while completely avoiding the difficult segmentation problem. Furthermore, an implicit language model is developed to make predictions based on semantic context within a predicting feature sequence, providing a new perspective for incorporating lexicon constraints and prior knowledge about a certain language in the recognition procedure. Experiments on two standard benchmarks, Dataset-CASIA and Dataset-ICDAR, yielded outstanding results, with correct rates of 97.50 and 96.58 percent, respectively, which are significantly better than the best result reported thus far in the literature. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

To describe trans-dimensional observations in sample spaces of different dimensions, we propose a probabilistic model, called the trans-dimensional random field (TRF) by explicitly mixing a collection of random fields. In the framework of stochastic approximation (SA), we develop an effective training algorithm, called augmented SA, which jointly estimates the model parameters and normalizing constants while using trans-dimensional mixture sampling to generate observations of different dimensions. Furthermore, we introduce several statistical and computational techniques to improve the convergence of the training algorithm and reduce computational cost, which together enable us to successfully train TRF models on large datasets. The new model and training algorithm are thoroughly evaluated in a number of experiments. The word morphology experiment provides a benchmark test to study the convergence of the training algorithm and to compare with other algorithms, because log-likelihoods and gradients can be exactly calculated in this experiment. For language modeling, our experiments demonstrate the superiority of the TRF approach in being computationally more efficient in computing data probabilities by avoiding local normalization and being able to flexibly integrate a richer set of features, when compared with n-gram models and neural network models. [ABSTRACT FROM PUBLISHER]

There is a large variation in the activities that humans perform in their everyday lives. We consider modeling these composite human activities which comprises multiple basic level actions in a completely unsupervised setting. Our model learns high-level co-occurrence and temporal relations between the actions. We consider the video as a sequence of short-term action clips, which contains human-words and object-words. An activity is about a set of action-topics and object-topics indicating which actions are present and which objects are interacting with. We then propose a new probabilistic model relating the words and the topics. It allows us to model long-range action relations that commonly exist in the composite activities, which is challenging in previous works. We apply our model to the unsupervised action segmentation and clustering, and to a novel application that detects forgotten actions, which we call action patching. For evaluation, we contribute a new challenging RGB-D activity video dataset recorded by the new Kinect v2, which contains several human daily activities as compositions of multiple actions interacting with different objects. Moreover, we develop a robotic system that watches and reminds people using our action patching algorithm. Our robotic setup can be easily deployed on any assistive robots. [ABSTRACT FROM PUBLISHER]

Since the observables at particular time instants in a temporal sequence exhibit dependencies, they are not independent samples. Thus, it is not plausible to apply i.i.d. assumption-based dimensionality reduction methods to sequence data. This paper presents a novel supervised dimensionality reduction approach for sequence data, called Linear Sequence Discriminant Analysis (LSDA). It learns a linear discriminative projection of the feature vectors in sequences to a lower-dimensional subspace by maximizing the separability of the sequence classes such that the entire sequences are holistically discriminated. The sequence class separability is constructed based on the sequence statistics, and the use of different statistics produces different LSDA methods. This paper presents and compares two novel LSDA methods, namely M-LSDA and D-LSDA. M-LSDA extracts model-based statistics by exploiting the dynamical structure of the sequence classes, and D-LSDA extracts the distance-based statistics by computing the pairwise similarity of samples from the same sequence class. Extensive experiments on several different tasks have demonstrated the effectiveness and the general applicability of the proposed methods. [ABSTRACT FROM AUTHOR]

This paper presents a method, called AOGTracker, for simultaneously tracking, learning and parsing (TLP) of unknown objects in video sequences with a hierarchical and compositional And-Or graph (AOG) representation. The TLP method is formulated in the Bayesian framework with a spatial and a temporal dynamic programming (DP) algorithms inferring object bounding boxes on-the-fly. During online learning, the AOG is discriminatively learned using latent SVM [1] to account for appearance (e.g., lighting and partial occlusion) and structural (e.g., different poses and viewpoints) variations of a tracked object, as well as distractors (e.g., similar objects) in background. Three key issues in online inference and learning are addressed: (i) maintaining purity of positive and negative examples collected online, (ii) controling model complexity in latent structure learning, and (iii) identifying critical moments to re-learn the structure of AOG based on its intrackability. The intrackability measures uncertainty of an AOG based on its score maps in a frame. In experiments, our AOGTracker is tested on two popular tracking benchmarks with the same parameter setting: the TB-100/50/CVPR2013 benchmarks [2] , [3] , and the VOT benchmarks [4] —VOT 2013, 2014, 2015 and TIR2015 (thermal imagery tracking). In the former, our AOGTracker outperforms state-of-the-art tracking algorithms including two trackers based on deep convolutional network   [5] , [6] . In the latter, our AOGTracker outperforms all other trackers in VOT2013 and is comparable to the state-of-the-art methods in VOT2014, 2015 and TIR2015. [ABSTRACT FROM PUBLISHER]

Current video event recognition research remains largely target-centered. For real-world surveillance videos, target-centered event recognition faces great challenges due to large intra-class target variation, limited image resolution, and poor detection and tracking results. To mitigate these challenges, we introduced a context-augmented video event recognition approach. Specifically, we explicitly capture different types of contexts from three levels including image level, semantic level, and prior level. At the image level, we introduce two types of contextual features including the appearance context features and interaction context features to capture the appearance of context objects and their interactions with the target objects. At the semantic level, we propose a deep model based on deep Boltzmann machine to learn event object representations and their interactions. At the prior level, we utilize two types of prior-level contexts including scene priming and dynamic cueing. Finally, we introduce a hierarchical context model that systematically integrates the contextual information at different levels. Through the hierarchical context model, contexts at different levels jointly contribute to the event recognition. We evaluate the hierarchical context model for event recognition on benchmark surveillance video datasets. Results show that incorporating contexts in each level can improve event recognition performance, and jointly integrating three levels of contexts through our hierarchical model achieves the best performance. [ABSTRACT FROM AUTHOR]

Trajectory analysis is essential in many applications. In this paper, we address the problem of representing motion trajectories in a highly informative way, and consequently utilize it for analyzing trajectories. Our approach first leverages the complete information from given trajectories to construct a thermal transfer field which provides a context-rich way to describe the global motion pattern in a scene. Then, a 3D tube is derived which depicts an input trajectory by integrating its surrounding motion patterns contained in the thermal transfer field. The 3D tube effectively: 1) maintains the movement information of a trajectory, 2) embeds the complete contextual motion pattern around a trajectory, 3) visualizes information about a trajectory in a clear and unified way. We further introduce a droplet-based process. It derives a droplet vector from a 3D tube, so as to characterize the high-dimensional 3D tube information in a simple but effective way. Finally, we apply our tube-and-droplet representation to trajectory analysis applications including trajectory clustering, trajectory classification & abnormality detection, and 3D action recognition. Experimental comparisons with state-of-the-art algorithms demonstrate the effectiveness of our approach. [ABSTRACT FROM PUBLISHER]

Pooling plays an important role in generating a discriminative video representation. In this paper, we propose a new semantic pooling approach for challenging event analysis tasks (e.g., event detection, recognition, and recounting) in long untrimmed Internet videos, especially when only a few shots/segments are relevant to the event of interest while many other shots are irrelevant or even misleading. The commonly adopted pooling strategies aggregate the shots indifferently in one way or another, resulting in a great loss of information. Instead, in this work we first define a novel notion of semantic saliency that assesses the relevance of each shot with the event of interest. We then prioritize the shots according to their saliency scores since shots that are semantically more salient are expected to contribute more to the final event analysis. Next, we propose a new isotonic regularizer that is able to exploit the constructed semantic ordering information. The resulting nearly-isotonic support vector machine classifier exhibits higher discriminative power in event analysis tasks. Computationally, we develop an efficient implementation using the proximal gradient algorithm, and we prove new and closed-form proximal steps. We conduct extensive experiments on three real-world video datasets and achieve promising improvements. [ABSTRACT FROM PUBLISHER]

In this paper, we present a 4D human-object interaction (4DHOI) model for solving three vision tasks jointly: i) event segmentation from a video sequence, ii) event recognition and parsing, and iii) contextual object localization. The 4DHOI model represents the geometric, temporal, and semantic relations in daily events involving human-object interactions. In 3D space, the interactions of human poses and contextual objects are modeled by semantic co-occurrence and geometric compatibility. On the time axis, the interactions are represented as a sequence of atomic event transitions with coherent objects. The 4DHOI model is a hierarchical spatial-temporal graph representation which can be used for inferring scene functionality and object affordance. The graph structures and parameters are learned using an ordered expectation maximization algorithm which mines the spatial-temporal structures of events from RGB-D video samples. Given an input RGB-D video, the inference is performed by a dynamic programming beam search algorithm which simultaneously carries out event segmentation, recognition, and object localization. We collected a large multiview RGB-D event dataset which contains 3,815 video sequences and 383,036 RGB-D frames captured by three RGB-D cameras. The experimental results on three challenging datasets demonstrate the strength of the proposed method. [ABSTRACT FROM AUTHOR]

We describe Google's online handwriting recognition system that currently supports 22 scripts and 97 languages. The system's focus is on fast, high-accuracy text entry for mobile, touch-enabled devices. We use a combination of state-of-the-art components and combine them with novel additions in a flexible framework. This architecture allows us to easily transfer improvements between languages and scripts. This made it possible to build recognizers for languages that, to the best of our knowledge, are not handled by any other online handwriting recognition system. The approach also enabled us to use the same architecture both on very powerful machines for recognition in the cloud as well as on mobile devices with more limited computational power by changing some of the settings of the system. In this paper we give a general overview of the system architecture and the novel components, such as unified time- and position-based input interpretation, trainable segmentation, minimum-error rate training for feature combination, and a cascade of pruning strategies. We present experimental results for different setups. The system is currently publicly available in several Google products, for example in Google Translate and as an input method for Android devices. [ABSTRACT FROM AUTHOR]

We propose a function-based temporal pooling method that captures the latent structure of the video sequence data - e.g., how frame-level features evolve over time in a video. We show how the parameters of a function that has been fit to the video data can serve as a robust new video representation. As a specific example, we learn a pooling function via ranking machines. By learning to rank the frame-level features of a video in chronological order, we obtain a new representation that captures the video-wide temporal dynamics of a video, suitable for action recognition. Other than ranking functions, we explore different parametric models that could also explain the temporal changes in videos. The proposed functional pooling methods, and rank pooling in particular, is easy to interpret and implement, fast to compute and effective in recognizing a wide variety of actions. We evaluate our method on various benchmarks for generic action, fine-grained action and gesture recognition. Results show that rank pooling brings an absolute improvement of 7-10 average pooling baseline. At the same time, rank pooling is compatible with and complementary to several appearance and local motion based methods and features, such as improved trajectories and deep learning features. [ABSTRACT FROM PUBLISHER]

Automatic facial action unit (AU) and expression detection from videos is a long-standing problem. The problem is challenging in part because classifiers must generalize to previously unknown subjects that differ markedly in behavior and facial morphology (e.g., heavy versus delicate brows, smooth versus deeply etched wrinkles) from those on which the classifiers are trained. While some progress has been achieved through improvements in choices of features and classifiers, the challenge occasioned by individual differences among people remains. Person-specific classifiers would be a possible solution but for a paucity of training data. Sufficient training data for person-specific classifiers typically is unavailable. This paper addresses the problem of how to personalize a generic classifier without additional labels from the test subject. We propose a transductive learning method, which we refer to as a Selective Transfer Machine (STM), to personalize a generic classifier by attenuating person-specific mismatches. STM achieves this effect by simultaneously learning a classifier and re-weighting the training samples that are most relevant to the test subject. We compared STM to both generic classifiers and cross-domain learning methods on four benchmarks: CK+ [44] , GEMEP-FERA [67] , RU-FACS [4] and GFT [57] . STM outperformed generic classifiers in all. [ABSTRACT FROM PUBLISHER]

This paper presents a shape-theoretic framework for dynamical analysis of nonlinear dynamical systems which appear frequently in several video-based inference tasks. Traditional approaches to dynamical modeling have included linear and nonlinear methods with their respective drawbacks. A novel approach we propose is the use of descriptors of the shape of the dynamical attractor as a feature representation of nature of dynamics. The proposed framework has two main advantages over traditional approaches: a) representation of the dynamical system is derived directly from the observational data, without any inherent assumptions, and b) the proposed features show stability under different time-series lengths where traditional dynamical invariants fail. We illustrate our idea using nonlinear dynamical models such as Lorenz and Rossler systems, where our feature representations (shape distribution) support our hypothesis that the local shape of the reconstructed phase space can be used as a discriminative feature. Our experimental analyses on these models also indicate that the proposed framework show stability for different time-series lengths, which is useful when the available number of samples are small/variable. The specific applications of interest in this paper are: 1) activity recognition using motion capture and RGBD sensors, 2) activity quality assessment for applications in stroke rehabilitation, and 3) dynamical scene classification. We provide experimental validation through action and gesture recognition experiments on motion capture and Kinect datasets. In all these scenarios, we show experimental evidence of the favorable properties of the proposed representation. [ABSTRACT FROM AUTHOR]

Soft biometrics have been emerging to complement other traits and are particularly useful for poor quality data. In this paper, we propose an efficient algorithm to estimate human head poses and to infer soft biometric labels based on the 3D morphology of the human head. Starting by considering a set of pose hypotheses, we use a learning set of head shapes synthesized from anthropometric surveys to derive a set of 3D head centroids that constitutes a metric space. Next, representing queries by sets of 2D head landmarks, we use projective geometry techniques to rank efficiently the joint 3D head centroids/pose hypotheses according to their likelihood of matching each query. The rationale is that the most likely hypotheses are sufficiently close to the query, so a good solution can be found by convex energy minimization techniques. Once a solution has been found, the 3D head centroid and the query are assumed to have similar morphology, yielding the soft label. Our experiments point toward the usefulness of the proposed solution, which can improve the effectiveness of face recognizers and can also be used as a privacy-preserving solution for biometric recognition in public environments. [ABSTRACT FROM AUTHOR]

There are many scenarios in artificial intelligence, signal processing or medicine, in which a temporal sequence consists of several unknown overlapping independent causes, and we are interested in accurately recovering those canonical causes. Factorial hidden Markov models (FHMMs) present the versatility to provide a good fit to these scenarios. However, in some scenarios, the number of causes or the number of states of the FHMM cannot be known or limited a priori. In this paper, we propose an infinite factorial unbounded-state hidden Markov model (IFUHMM), in which the number of parallel hidden Markovmodels (HMMs) and states in each HMM are potentially unbounded. We rely on a Bayesian nonparametric (BNP) prior over integer-valued matrices, in which the columns represent the Markov chains, the rows the time indexes, and the integers the state for each chain and time instant. First, we extend the existent infinite factorial binary-state HMM to allow for any number of states. Then, we modify this model to allow for an unbounded number of states and derive an MCMC-based inference algorithm that properly deals with the trade-off between the unbounded number of states and chains. We illustrate the performance of our proposed models in the power disaggregation problem. [ABSTRACT FROM AUTHOR]

We address the video-based face association problem, in which one attempts to extract the face tracks of multiple subjects while maintaining label consistency. Traditional tracking algorithms have difficulty in handling this task, especially when challenging nuisance factors like motion blur, low resolution or significant camera motions are present. We demonstrate that contextual features, in addition to face appearance itself, play an important role in this case. We propose principled methods to combine multiple features using Conditional Random Fields and Max-Margin Markov networks to infer labels for the detected faces. Different from many existing approaches, our algorithms work in online mode and hence have a wider range of applications. We address issues such as parameter learning, inference and handling false positves/negatives that arise in the proposed approach. Finally, we evaluate our approach on several public databases. [ABSTRACT FROM AUTHOR]

We present a new gesture recognition method that is based on the conditional random field (CRF) model using multiple feature matching. Our approach solves the labeling problem, determining gesture categories and their temporal ranges at the same time. A generative probabilistic model is formalized and probability densities are nonparametrically estimated by matching input features with a training dataset. In addition to the conventional skeletal joint-based features, the appearance information near the active hand in an RGB image is exploited to capture the detailed motion of fingers. The estimated likelihood function is then used as the unary term for our CRF model. The smoothness term is also incorporated to enforce the temporal coherence of our solution. Frame-wise recognition results can then be obtained by applying an efficient dynamic programming technique. To estimate the parameters of the proposed CRF model, we incorporate the structured support vector machine (SSVM) framework that can perform efficient structured learning by using large-scale datasets. Experimental results demonstrate that our method provides effective gesture recognition results for challenging real gesture datasets. By scoring 0.8563 in the mean Jaccard index, our method has obtained the state-of-the-art results for the gesture recognition track of the 2014 ChaLearn Looking at People (LAP) Challenge. [ABSTRACT FROM PUBLISHER]

This paper describes a novel method called Deep Dynamic Neural Networks (DDNN) for multimodal gesture recognition. A semi-supervised hierarchical dynamic framework based on a Hidden Markov Model (HMM) is proposed for simultaneous gesture segmentation and recognition where skeleton joint information, depth and RGB images, are the multimodal input observations. Unlike most traditional approaches that rely on the construction of complex handcrafted features, our approach learns high-level spatio-temporal representations using deep neural networks suited to the input modality: a Gaussian-Bernouilli Deep Belief Network (DBN) to handle skeletal dynamics, and a 3D Convolutional Neural Network (3DCNN) to manage and fuse batches of depth and RGB images. This is achieved through the modeling and learning of the emission probabilities of the HMM required to infer the gesture sequence. This purely data driven approach achieves a Jaccard index score of 0.81 in the ChaLearn LAP gesture spotting challenge. The performance is on par with a variety of state-of-the-art hand-tuned feature-based approaches and other learning-based methods, therefore opening the door to the use of deep learning techniques in order to further explore multimodal time series data. [ABSTRACT FROM PUBLISHER]

Availability of handy RGB-D sensors has brought about a surge of gesture recognition research and applications. Among various approaches, one shot learning approach is advantageous because it requires minimum amount of data. Here, we provide a thorough review about one-shot learning gesture recognition from RGB-D data and propose a novel spatiotemporal feature extracted from RGB-D data, namely mixed features around sparse keypoints (MFSK). In the review, we analyze the challenges that we are facing, and point out some future research directions which may enlighten researchers in this field. The proposed MFSK feature is robust and invariant to scale, rotation and partial occlusions. To alleviate the insufficiency of one shot training samples, we augment the training samples by artificially synthesizing versions of various temporal scales, which is beneficial for coping with gestures performed at varying speed. We evaluate the proposed method on the Chalearn gesture dataset (CGD). The results show that our approach outperforms all currently published approaches on the challenging data of CGD, such as translated, scaled and occluded subsets. When applied to the RGB-D datasets that are not one-shot (e.g., the Cornell Activity Dataset-60 and MSR Daily Activity 3D dataset), the proposed feature also produces very promising results under leave-one-out cross validation or one-shot learning. [ABSTRACT FROM PUBLISHER]

Automatic behavior analysis from video is a major topic in many areas of research, including computer vision, multimedia, robotics, biology, cognitive science, social psychology, psychiatry, and linguistics. Two major problems are of interest when analyzing behavior. First, we wish to automatically categorize observed behaviors into a discrete set of classes (i.e., classification). For example, to determine word production from video sequences in sign language. Second, we wish to understand the relevance of each behavioral feature in achieving this classification (i.e., decoding). For instance, to know which behavior variables are used to discriminate between the words apple and onion in American Sign Language (ASL). The present paper proposes to model behavior using a labeled graph, where the nodes define behavioral features and the edges are labels specifying their order (e.g., before, overlaps, start). In this approach, classification reduces to a simple labeled graph matching. Unfortunately, the complexity of labeled graph matching grows exponentially with the number of categories we wish to represent. Here, we derive a graph kernel to quickly and accurately compute this graph similarity. This approach is very general and can be plugged into any kernel-based classifier. Specifically, we derive a Labeled Graph Support Vector Machine (LGSVM) and a Labeled Graph Logistic Regressor (LGLR) that can be readily employed to discriminate between many actions (e.g., sign language concepts). The derived approach can be readily used for decoding too, yielding invaluable information for the understanding of a problem (e.g., to know how to teach a sign language). The derived algorithms allow us to achieve higher accuracy results than those of state-of-the-art algorithms in a fraction of the time. We show experimental results on a variety of problems and datasets, including multimodal data. [ABSTRACT FROM PUBLISHER]

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. [ABSTRACT FROM PUBLISHER]

We present a novel non-parametric Bayesian model to jointly discover the dynamics of low-level actions and high-level behaviors of tracked objects. In our approach, actions capture both linear, low-level object dynamics, and an additional spatial distribution on where the dynamic occurs. Furthermore, behavior classes capture high-level temporal motion dependencies in Markov chains of actions, thus each learned behavior is a switching linear dynamical system. The number of actions and behaviors is discovered from the data itself using Dirichlet Processes. We are especially interested in cases where tracks can exhibit large kinematic and spatial variations, e.g. person tracks in open environments, as found in the visual surveillance and intelligent vehicle domains. The model handles real-valued features directly, so no information is lost by quantizing measurements into ‘visual words’, and variations in standing, walking and running can be discovered without discrete thresholds. We describe inference using Markov Chain Monte Carlo sampling and validate our approach on several artificial and real-world pedestrian track datasets from the surveillance and intelligent vehicle domain. We show that our model can distinguish between relevant behavior patterns that an existing state-of-the-art hierarchical model for clustering and simpler model variants cannot. The software and the artificial and surveillance datasets are made publicly available for benchmarking purposes. [ABSTRACT FROM PUBLISHER]