Guangping Xu

Multi-perspective and multi-modality joint representation and recognition model for 3D action recognition

Abstract In this paper, we proposed multi-perspective and multi-modality discriminated and joint representation and recognition model for 3D action recognition. Specifically, for depth and RGB image sequence, we construct a novel difference motion history image, and then propose multi-perspective projections to capture the target motion process, after that, pyramid histogram of orientated gradients is extracted for each projection to describe the target motion, finally, multi-perspective and multi-modality discriminated and joint representation and recognition model is proposed to recognize human action. Large scale experimental results on challenging and public DHA 3D and MSR-Action3D action datasets show that the performances of our difference motion history image on two modalities are much better than traditional motion history image, at the same time, our description scheme is also very robust and efficient, what is more, our proposed multi-perspective and multi-modality discriminated and joint representation and recognition model further improves the performance, which outperforms the state-of-the-art methods, and whose best performances on MSR-Action3D and DHA datasets reach 90.5% and 98.2% respectively.

Human Action Recognition Via Multi-modality Information

In this paper, we propose pyramid appearance and global structure action descriptors on both RGB and depth motion history images and a model-free method for human action recognition. In proposed algorithm, we firstly construct motion history image for both RGB and depth channels, at the same time, depth information is employed to filter RGB information, after that, different action descriptors are extracted from depth and RGB MHIs to represent these actions, and then multimodality information collaborative representation and recognition model, in which multi-modality information are put into object function naturally, and information fusion and action recognition also be done together, is proposed to classify human actions. To demonstrate the superiority of the proposed method, we evaluate it on MSR Action3D and DHA datasets, the well-known dataset for human action recognition. Large scale experiment shows our descriptors are robust, stable and efficient, when comparing with the-state-of-the-art algorithms, the performances of our descriptors are better than that of them, further, the performance of combined descriptors is much better than just using sole descriptor. What is more, our proposed model outperforms the state-of-the-art methods on both MSR Action3D and DHA datasets.

Human Action Recognition Using Pyramid Histograms of Oriented Gradients and Collaborative Multi-task Learning

In this paper, human action recognition using pyramid histograms of oriented gradients and collaborative multi-task learning is proposed. First, we accumulate global activities and construct motion history image (MHI) for both RGB and depth channels respectively to encode the dynamics of one action in different modalities, and then different action descriptors are extracted from depth and RGB MHI to represent global textual and structural characteristics of these actions. Specially, average value in hierarchical block, GIST and pyramid histograms of oriented gradients descriptors are employed to represent human motion. To demonstrate the superiority of the proposed method, we evaluate them by KNN, SVM with linear and RBF kernels, SRC and CRC models on DHA dataset, the well-known dataset for human action recognition. Large scale experimental results show our descriptors are robust, stable and efficient, and outperform the state-of-the-art methods. In addition, we investigate the performance of our descriptors further by combining these descriptors on DHA dataset, and observe that the performances of combined descriptors are much better than just using only sole descriptor. With multimodal features, we also propose a collaborative multi-task learning method for model learning and inference based on transfer learning theory. The main contributions lie in four aspects: 1) the proposed encoding the scheme can filter the stationary part of human body and reduce noise interference; 2) different kind of features and models are assessed, and the neighbor gradients information and pyramid layers are very helpful for representing these actions; 3) The proposed model can fuse the features from different modalities regardless of the sensor types, the ranges of the value, and the dimensions of different features; 4) The latent common knowledge among different modalities can be discovered by transfer learning to boost the performance.

Human action recognition on depth dataset

Abstract Human action recognition is a hot research topic; however, the change in shapes, the high variability of appearances, dynamitic background, potential occlusions in different actions and the image limit of 2D sensor make it more difficult. To solve these problems, we pay more attention to the depth channel and the fusion of different features. Thus, we firstly extract different features for depth image sequence, and then, multi-feature mapping and dictionary learning model (MMDLM) is proposed to deeply discover the relationship between these different features, where two dictionaries and a feature mapping function are simultaneously learned. What is more, these dictionaries can fully characterize the structure information of different features, while the feature mapping function is a regularization term, which can reveal the intrinsic relationship between these two features. Large-scale experiments on two public depth datasets, MSRAction3D and DHA, show that the performances of these different depth features have a big difference, but they are complementary. Further, the features fusion by MMDLM is very efficient and effective on both datasets, which is comparable to the state-of-the-art methods.

HERO: Heterogeneity-aware erasure coded redundancy optimal allocation for reliable storage in distributed networks

Heterogeneity is the natural feature in distributed networks. Different from the traditional disk array, the amount of data allocated on heterogenous peers may be not the same. To maximize the reliability of stored data objects in heterogeneous networks, the optimal allocation of erasure-coded fragments is a challenging problem constrained with heterogeneous peer availabilities and redundancy overhead. This paper examines this optimal problem considered MDS erasure codes applied into distributed storage networks. First, we model the reliability of an allocation with the weighted-k-out-of-s model and extend its properties to efficiently calculate the reliability of an allocation; then we reduce the reliability computation of a given allocation to linear computation cost based on the weighted k-out-of-s model. Then, we deduce the problem to integer partition problem and propose two order-based search algorithms. Our experiments show that our proposed algorithms can be applied to find the optimal allocations efficiently in various practical coding cases. Furthermore, we evaluate the performance of our proposed search algorithms with some practical storage settings, and then present experimental results including the reliability, redundancy overheads and allocation pattern for the optimal allocation driven by practical network traces.

Churn Impact on Replicated Data Duration in Structured P2P Networks

This paper analyzes churn impact on replicated data duration with different node lifetime distributions. In structured overlay networks, churn includes node-join churn and node-failure churn, caused by the arrival and departure of nodes separately. The paper introduces a duration model of replicated data under node-failure churn for node failure directly leads to data loss. Furthermore, it investigates the impact of node-join churn on the duration of replicated data for different node-lifetime distributions. The paper presents that node-churn will negatively impact on replicated data duration for heavy-tailed distribution and Weibull distribution except exponential distribution. Then we evaluate the impact on replicated data duration with two real-world trace datasets. The experimental results show the negative impact of node-join churn for different node-join churn degrees. Finally, the paper discusses an enhancement by setting a trial period for every fresh node. By experiment, it is an effective way to reduce the negative impact of node-join churn due to the memory property of node lifetime distributions.

A Fast 3D Retrieval Algorithm via Class-Statistic and Pair-Constraint Model

With the development of 3D technologies and devices, 3D model retrieval becomes a hot research topic where multi-view matching algorithms have demonstrated satisfying performance. However, exciting works overlook the common factors among objects in a single class, and they are time consuming in retrieval processing. In this paper, a class-statistics and pair-constraint model (CSPC) method is originally proposed for 3D model retrieval, which is composed of supervised class-based statistics model and pair-constraint object retrieval model. In our CSPC model, we firstly convert view-based distance measure into object-based distance measure without falling in performance, which will advance 3D model retrieval speed. Secondly, the generality of the distribution of each feature dimension in each class is computed to judge category information, and then we further adopt this distribution information to build class models. Finally, an object-based pairwise constraint is introduced on the base of the class-statistic measure, which can remove a lot of false alarm samples in retrieval. Experimental results on ETH, NTU-60, MVRED and PSB 3D datasets show that our method is fast, and its performance is also comparable with the-state-of-the-art algorithms.

Multi-dimensional human action recognition model based on image set and group sparisty

Abstract Human action recognition is a hot research topic in computer vision, which has been applied into surveillance system and human machine interface. However, since the high variability of appearance, shapes and potential occlusions, single-view human action recognition task is challenging, thus, in this paper, we proposed multi-dimensional human action recognition model based on image set and group sparsity. Specifically, we first extract dense trajectory feature for each camera, and then construct the shared codebook by k-means for all cameras, after that, Bag-of-Word ( BoW ) weight scheme is employed to code dense trajectory feature by the shared codebook for each camera respectively, and then multi-dimensional human action recognition model based on image set and group sparsity is trained where multi-view samples are considered as query set, and it is whole reconstructed by gallery set, at the same time, spare coefficients are requested to group sparsity. Large scale experimental results on three public multi-view action3D datasets – Northwestern UCLA, IXMAX and CVS-MV-RGBD-Single , show that multi-dimensional data is very helpful for action recognition, and the proposed scheme based on image set can further improve the performance, what is more, when group sparsity is added, its performance is comparable to the state-of-the-art methods.

Expander code: A scalable erasure-resilient code to keep up with data growth in distributed storage

To ensure high reliability and storage efficiency, erasure codes are preferred in storage systems. With the prevalent of distributed storage systems such as clouds storage, how to design a scalable and efficient erasure-resilient code is challenging. We propose a scalable binary linear code to keep up with data growth which has the following properties. Given the group size k and the code block length n, the proposed code corrects any two bit erasures among the n bits. The redundancy overhead of the code is 2/(k + 2), and each data bit affects exactly 2 parity bits. As results of these properties, if a data bit is changed or added, only two parity bits need to be updated; and the recovery of an erasured bit requires accessing at most k other bits and the recovery of two erasured bits requires at most 2k other bits. We give the construction algorithm by the order expansion of regular graphs; moreover, we optimize the failure resilience during the construction procedure. Compared with existing codes, our proposed code has notable benefits in storage scalability, redundancy overhead and I/O bandwidth. The deployment of the proposed code in distributed storage systems can be simple and practical.

A shape contour description method based on chain code and Fast Fourier Transform

A new shape contour description method based on eight-direction chain code and Fast Fourier Transform (FFT) is proposed. Firstly, chain code tracks shape boundary sequentially, according to the relationship between contour and chain-code projection-transform value. A constructed chain-code function of contour is transformed using FFT. After optimization, then a new Fourier Constant Factor Descriptor is proposed which is called FCFD. The descriptor is independent of initial point and has rotation, shift and scale (RSS) invariant properties. The results of experiments show that our shape contour description method based on FFT reduces computation and improves the efficiency of data processing effectively.