We introduce an approach to computing and comparing Covariance Descriptors (CovDs) in infinite-dimensional spaces. CovDs have become increasingly popular to address classification problems in computer vision. While CovDs offer some robustness to measurement variations, they also throw away part of the information contained in the original data by only retaining the second-order statistics over the measurements. Here, we propose to overcome this limitation by first mapping the original data to a high-dimensional Hilbert space, and only then compute the CovDs. We show that several Bregman divergences can be computed between the resulting CovDs in Hilbert space via the use of kernels. We then exploit these divergences for classification purposes. Our experiments demonstrate the benefits of our approach on several tasks, such as material and texture recognition, person re-identification, and action recognition from motion capture data.
Human pose estimation is one of the key problems in computer vision that has been studied in the recent years. The significance of human pose estimation is in the higher level tasks of understanding human actions applications such as recognition of anomalous actions present in videos and many other related applications. The human poses can be estimated by extracting silhouettes of humans as silhouettes are robust to variations and it gives the shape information of the human body. Some common challenges include illumination changes, variation in environments, and variation in human appearances. Thus there is a need for a robust method for human pose estimation. This paper presents a study and analysis of approaches existing for silhouette extraction and proposes a robust technique for extracting human silhouettes in video sequences. Gaussian Mixture Model (GMM) A statistical approach is combined with HSV (Hue, Saturation and Value) color space model for a robust background model that is used for background subtraction to produce foreground blobs, called human silhouettes. Morphological operations are then performed on foreground blobs from background subtraction. The silhouettes obtained from this work can be used in further tasks associated with human action interpretation and activity processes like human action classification, human pose estimation and action recognition or action interpretation.
Historically, researchers in the field have spent a great deal of effort to create image representations that have scale invariance and retain spatial location information. This paper proposes to encode equivalent temporal characteristics in video representations for action recognition. To achieve temporal scale invariance, we develop a method called temporal scale pyramid (TSP). To encode temporal information, we present and compare two methods called temporal extension descriptor (TED) and temporal division pyramid (TDP) . Our purpose is to suggest solutions for matching complex actions that have large variation in velocity and appearance, which is missing from most current action representations. The experimental results on four benchmark datasets, UCF50, HMDB51, Hollywood2 and Olympic Sports, support our approach and significantly outperform state-of-the-art methods. Most noticeably, we achieve 65.0% mean accuracy and 68.2% mean average precision on the challenging HMDB51 and Hollywood2 datasets which constitutes an absolute improvement over the state-of-the-art by 7.8% and 3.9%, respectively.
In this paper, we describe a simple strategy for mitigating variability in temporal data series by shifting focus onto long-term, frequency domain features that are less susceptible to variability. We apply this method to the human action recognition task and demonstrate how working in the frequency domain can yield good recognition features for commonly used optical flow and articulated pose features, which are highly sensitive to small differences in motion, viewpoint, dynamic backgrounds, occlusion and other sources of variability. We show how these frequency-based features can be used in combination with a simple forest classifier to achieve good and robust results on the popular KTH Actions dataset.
This paper introduces sparse coding and dictionary learning for Symmetric Positive Definite (SPD) matrices, which are often used in machine learning, computer vision and related areas. Unlike traditional sparse coding schemes that work in vector spaces, in this paper we discuss how SPD matrices can be described by sparse combination of dictionary atoms, where the atoms are also SPD matrices. We propose to seek sparse coding by embedding the space of SPD matrices into Hilbert spaces through two types of Bregman matrix divergences. This not only leads to an efficient way of performing sparse coding, but also an online and iterative scheme for dictionary learning. We apply the proposed methods to several computer vision tasks where images are represented by region covariance matrices. Our proposed algorithms outperform state-of-the-art methods on a wide range of classification tasks, including face recognition, action recognition, material classification and texture categorization.
Recently, mid-level features have shown promising performance in computer vision. Mid-level features learned by incorporating class-level information are potentially more discriminative than traditional low-level local features. In this paper, an effective method is proposed to extract mid-level features from Kinect skeletons for 3D human action recognition. Firstly, the orientations of limbs connected by two skeleton joints are computed and each orientation is encoded into one of the 27 states indicating the spatial relationship of the joints. Secondly, limbs are combined into parts and the limb's states are mapped into part states. Finally, frequent pattern mining is employed to mine the most frequent and relevant (discriminative, representative and non-redundant) states of parts in continuous several frames. These parts are referred to as Frequent Local Parts or FLPs. The FLPs allow us to build powerful bag-of-FLP-based action representation. This new representation yields state-of-the-art results on MSR DailyActivity3D and MSR ActionPairs3D.
In the field of gestural action recognition, many studies have focused on dimensionality reduction along the spatial axis, to reduce both the variability of gestural sequences expressed in the reduced space, and the computational complexity of their processing. It is noticeable that very few of these methods have explicitly addressed the dimensionality reduction along the time axis. This is however a major issue with regard to the use of elastic distances characterized by a quadratic complexity. To partially fill this apparent gap, we present in this paper an approach based on temporal down-sampling associated to elastic kernel machine learning. We experimentally show, on two data sets that are widely referenced in the domain of human gesture recognition, and very different in terms of quality of motion capture, that it is possible to significantly reduce the number of skeleton frames while maintaining a good recognition rate. The method proves to give satisfactory results at a level currently reached by state-of-the-art methods on these data sets. The computational complexity reduction makes this approach eligible for real-time applications.
Existing techniques for 3D action recognition are sensitive to viewpoint variations because they extract features from depth images which change significantly with viewpoint. In contrast, we directly process the pointclouds and propose a new technique for action recognition which is more robust to noise, action speed and viewpoint variations. Our technique consists of a novel descriptor and keypoint detection algorithm. The proposed descriptor is extracted at a point by encoding the Histogram of Oriented Principal Components (HOPC) within an adaptive spatio-temporal support volume around that point. Based on this descriptor, we present a novel method to detect Spatio-Temporal Key-Points (STKPs) in 3D pointcloud sequences. Experimental results show that the proposed descriptor and STKP detector outperform state-of-the-art algorithms on three benchmark human activity datasets. We also introduce a new multiview public dataset and show the robustness of our proposed method to viewpoint variations.
We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between frames. We also aim to generalise the best performing hand-crafted features within a data-driven learning framework. Our contribution is three-fold. First, we propose a two-stream ConvNet architecture which incorporates spatial and temporal networks. Second, we demonstrate that a ConvNet trained on multi-frame dense optical flow is able to achieve very good performance in spite of limited training data. Finally, we show that multi-task learning, applied to two different action classification datasets, can be used to increase the amount of training data and improve the performance on both. Our architecture is trained and evaluated on the standard video actions benchmarks of UCF-101 and HMDB-51, where it is competitive with the state of the art. It also exceeds by a large margin previous attempts to use deep nets for video classification.
As a fundamental technique that concerns several vision tasks such as image parsing, action recognition and clothing retrieval, human pose estimation (HPE) has been extensively investigated in recent years. To achieve accurate and reliable estimation of the human pose, it is well-recognized that the clothing attributes are useful and should be utilized properly. Most previous approaches, however, require to manually annotate the clothing attributes and are therefore very costly. In this paper, we shall propose and explore a \emph{latent} clothing attribute approach for HPE. Unlike previous approaches, our approach models the clothing attributes as latent variables and thus requires no explicit labeling for the clothing attributes. The inference of the latent variables are accomplished by utilizing the framework of latent structured support vector machines (LSSVM). We employ the strategy of \emph{alternating direction} to train the LSSVM model: In each iteration, one kind of variables (e.g., human pose or clothing attribute) are fixed and the others are optimized. Our extensive experiments on two real-world benchmarks show the state-of-the-art performance of our proposed approach.
This paper introduces a high efficient local spatiotemporal descriptor, called gradient boundary histograms (GBH). The proposed GBH descriptor is built on simple spatio-temporal gradients, which are fast to compute. We demonstrate that it can better represent local structure and motion than other gradient-based descriptors, and significantly outperforms them on large realistic datasets. A comprehensive evaluation shows that the recognition accuracy is preserved while the spatial resolution is greatly reduced, which yields both high efficiency and low memory usage.
Recently, deep learning approach has achieved promising results in various fields of computer vision. In this paper, a new framework called Hierarchical Depth Motion Maps (HDMM) + 3 Channel Deep Convolutional Neural Networks (3ConvNets) is proposed for human action recognition using depth map sequences. Firstly, we rotate the original depth data in 3D pointclouds to mimic the rotation of cameras, so that our algorithms can handle view variant cases. Secondly, in order to effectively extract the body shape and motion information, we generate weighted depth motion maps (DMM) at several temporal scales, referred to as Hierarchical Depth Motion Maps (HDMM). Then, three channels of ConvNets are trained on the HDMMs from three projected orthogonal planes separately. The proposed algorithms are evaluated on MSRAction3D, MSRAction3DExt, UTKinect-Action and MSRDailyActivity3D datasets respectively. We also combine the last three datasets into a larger one (called Combined Dataset) and test the proposed method on it. The results show that our approach can achieve state-of-the-art results on the individual datasets and without dramatical performance degradation on the Combined Dataset.
Persistent surveillance from camera networks, such as at parking lots, UAVs, etc., often results in large amounts of video data, resulting in significant challenges for inference in terms of storage, communication and computation. Compressive cameras have emerged as a potential solution to deal with the data deluge issues in such applications. However, inference tasks such as action recognition require high quality features which implies reconstructing the original video data. Much work in compressive sensing (CS) theory is geared towards solving the reconstruction problem, where state-of-the-art methods are computationally intensive and provide low-quality results at high compression rates. Thus, reconstruction-free methods for inference are much desired. In this paper, we propose reconstruction-free methods for action recognition from compressive cameras at high compression ratios of 100 and above. Recognizing actions directly from CS measurements requires features which are mostly nonlinear and thus not easily applicable. This leads us to search for such properties that are preserved in compressive measurements. To this end, we propose the use of spatio-temporal smashed filters, which are compressive domain versions of pixel-domain matched filters. We conduct experiments on publicly available databases and show that one can obtain recognition rates that are comparable to the oracle method in uncompressed setup, even for high compression ratios.
Human action recognition has been an important topic in computer vision due to its many applications such as video surveillance, human machine interaction and video retrieval. One core problem behind these applications is automatically recognizing low-level actions and high-level activities of interest. The former is usually the basis for the latter. This survey gives an overview of the most recent advances in human action recognition during the past several years, following a well-formed taxonomy proposed by a previous survey. From this state-of-the-art survey, researchers can view a panorama of progress in this area for future research.
Action recognition is an important problem in multimedia understanding. This paper addresses this problem by building an expressive compositional action model. We model one action instance in the video with an ensemble of spatio-temporal compositions: a number of discrete temporal anchor frames, each of which is further decomposed to a layout of deformable parts. In this way, our model can identify a Spatio-Temporal And-Or Graph (STAOG) to represent the latent structure of actions e.g. triple jumping, swinging and high jumping. The STAOG model comprises four layers: (i) a batch of leaf-nodes in bottom for detecting various action parts within video patches; (ii) the or-nodes over bottom, i.e. switch variables to activate their children leaf-nodes for structural variability; (iii) the and-nodes within an anchor frame for verifying spatial composition; and (iv) the root-node at top for aggregating scores over temporal anchor frames. Moreover, the contextual interactions are defined between leaf-nodes in both spatial and temporal domains. For model training, we develop a novel weakly supervised learning algorithm which iteratively determines the structural configuration (e.g. the production of leaf-nodes associated with the or-nodes) along with the optimization of multi-layer parameters. By fully exploiting spatio-temporal compositions and interactions, our approach handles well large intra-class action variance (e.g. different views, individual appearances, spatio-temporal structures). The experimental results on the challenging databases demonstrate superior performance of our approach over other competing methods.
Although dense local spatial-temporal features with bag-of-features representation achieve state-of-the-art performance for action recognition, the huge feature number and feature size prevent current methods from scaling up to real size problems. In this work, we investigate different types of feature sampling strategies for action recognition, namely dense sampling, uniformly random sampling and selective sampling. We propose two effective selective sampling methods using object proposal techniques. Experiments conducted on a large video dataset show that we are able to achieve better average recognition accuracy using 25% less features, through one of proposed selective sampling methods, and even remain comparable accuracy while discarding 70% features.
In this paper we propose a novel approach to multi-action recognition that performs joint segmentation and classification. This approach models each action using a Gaussian mixture using robust low-dimensional action features. Segmentation is achieved by performing classification on overlapping temporal windows, which are then merged to produce the final result. This approach is considerably less complicated than previous methods which use dynamic programming or computationally expensive hidden Markov models (HMMs). Initial experiments on a stitched version of the KTH dataset show that the proposed approach achieves an accuracy of 78.3%, outperforming a recent HMM-based approach which obtained 71.2%.
The number of categories for action recognition is growing rapidly. It is thus becoming increasingly hard to collect sufficient training data to learn conventional models for each category. This issue may be ameliorated by the increasingly popular 'zero-shot learning' (ZSL) paradigm. In this framework a mapping is constructed between visual features and a human interpretable semantic description of each category, allowing categories to be recognised in the absence of any training data. Existing ZSL studies focus primarily on image data, and attribute-based semantic representations. In this paper, we address zero-shot recognition in contemporary video action recognition tasks, using semantic word vector space as the common space to embed videos and category labels. This is more challenging because the mapping between the semantic space and space-time features of videos containing complex actions is more complex and harder to learn. We demonstrate that a simple self-training and data augmentation strategy can significantly improve the efficacy of this mapping. Experiments on human action datasets including HMDB51 and UCF101 demonstrate that our approach achieves the state-of-the-art zero-shot action recognition performance.
We propose a Bayesian approach to learn discriminative dictionaries for sparse representation of data. The proposed approach infers probability distributions over the atoms of a discriminative dictionary using a Beta Process. It also computes sets of Bernoulli distributions that associate class labels to the learned dictionary atoms. This association signifies the selection probabilities of the dictionary atoms in the expansion of class-specific data. Furthermore, the non-parametric character of the proposed approach allows it to infer the correct size of the dictionary. We exploit the aforementioned Bernoulli distributions in separately learning a linear classifier. The classifier uses the same hierarchical Bayesian model as the dictionary, which we present along the analytical inference solution for Gibbs sampling. For classification, a test instance is first sparsely encoded over the learned dictionary and the codes are fed to the classifier. We performed experiments for face and action recognition; and object and scene-category classification using five public datasets and compared the results with state-of-the-art discriminative sparse representation approaches. Experiments show that the proposed Bayesian approach consistently outperforms the existing approaches.
Statistical classification of actions in videos is mostly performed by extracting relevant features, particularly covariance features, from image frames and studying time series associated with temporal evolutions of these features. A natural mathematical representation of activity videos is in form of parameterized trajectories on the covariance manifold, i.e. the set of symmetric, positive-definite matrices (SPDMs). The variable execution-rates of actions implies variable parameterizations of the resulting trajectories, and complicates their classification. Since action classes are invariant to execution rates, one requires rate-invariant metrics for comparing trajectories. A recent paper represented trajectories using their transported square-root vector fields (TSRVFs), defined by parallel translating scaled-velocity vectors of trajectories to a reference tangent space on the manifold. To avoid arbitrariness of selecting the reference and to reduce distortion introduced during this mapping, we develop a purely intrinsic approach where SPDM trajectories are represented by redefining their TSRVFs at the starting points of the trajectories, and analyzed as elements of a vector bundle on the manifold. Using a natural Riemannain metric on vector bundles of SPDMs, we compute geodesic paths and geodesic distances between trajectories in the quotient space of this vector bundle, with respect to the re-parameterization group. This makes the resulting comparison of trajectories invariant to their re-parameterization. We demonstrate this framework on two applications involving video classification: visual speech recognition or lip-reading and hand-gesture recognition. In both cases we achieve results either comparable to or better than the current literature.