A spatial-temporal iterative tensor decomposition technique for action and gesture recognition

被引:0
|
作者
Yuting Su
Haiyi Wang
Peiguang Jing
Chuanzhong Xu
机构
[1] Tianjin University,School of Electronic Information Engineering
来源
Multimedia Tools and Applications | 2017年 / 76卷
关键词
Gesture recognition; Tensor decomposition; Spatial-temporal iterative; Video sequences;
D O I
暂无
中图分类号
学科分类号
摘要
Classification of video sequences is an important task with many applications in video search and action recognition. As opposed to some traditional approaches that transform original video sequences into forms of visual feature vectors, tensor-based methods have been proposed for classifying video sequences with natural representation of original data. However, one obvious limitation of tensor-based methods is that the input video sequences are often required to be preprocessed with a unified length of time. In this paper, we propose a technique for handling classification of video sequences in unequal length of time, namely Spatial-Temporal Iterative Tensor Decomposition (S-TITD) for uniform length. The proposed framework contains two primary steps. We first represent original video sequences as a third-order tensor and perform Tucker-2 decomposition to obtain the reduced-dimension core tensor. Then we encode the third order of core tensor to a uniform length by adaptively selecting the most informative slices. Notably, the above two steps are embedded into a dynamic learning framework to guarantee the proposed method has the ability of updating results over time. We conduct a series of experiments on three public datasets in gesture and action recognition, and the experimental results show that the proposed S-TITD approach achieves better performances than the state-of-the-art algorithms.
引用
收藏
页码:10635 / 10652
页数:17
相关论文
共 50 条
  • [21] Select and Focus: Action Recognition with Spatial-Temporal Attention
    Chan, Wensong
    Tian, Zhiqiang
    Liu, Shuai
    Ren, Jing
    Lan, Xuguang
    INTELLIGENT ROBOTICS AND APPLICATIONS, ICIRA 2019, PT III, 2019, 11742 : 461 - 471
  • [22] Spatial-Temporal Interleaved Network for Efficient Action Recognition
    Jiang, Shengqin
    Zhang, Haokui
    Qi, Yuankai
    Liu, Qingshan
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2025, 21 (01) : 178 - 187
  • [23] Tensor Decomposition for Spatial-Temporal Traffic Flow Prediction with Sparse Data
    Yang, Funing
    Liu, Guoliang
    Huang, Liping
    Chin, Cheng Siong
    SENSORS, 2020, 20 (21) : 1 - 15
  • [24] Spatial-Temporal Traffic Modeling With a Fusion Graph Reconstructed by Tensor Decomposition
    Li, Qin
    Yang, Xuan
    Wang, Yong
    Wu, Yuankai
    He, Deqiang
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2024, 25 (02) : 1749 - 1760
  • [25] Spatial-temporal saliency action mask attention network for action recognition
    Jiang, Min
    Pan, Na
    Kong, Jun
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2020, 71
  • [26] Hierarchy Spatial-Temporal Transformer for Action Recognition in Short Videos
    Cai, Guoyong
    Cai, Yumeng
    FUZZY SYSTEMS AND DATA MINING VI, 2020, 331 : 760 - 774
  • [27] Action Recognition Based on Spatial-Temporal Pyramid Sparse Coding
    Zhang, Xiaojing
    Zhang, Hua
    Cao, Xiaochun
    2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 1455 - 1458
  • [28] Hierarchical Spatial-Temporal Masked Contrast for Skeleton Action Recognition
    Cao, Wenming
    Zhang, Aoyu
    He, Zhihai
    Zhang, Yicha
    Yin, Xinpeng
    IEEE Transactions on Artificial Intelligence, 2024, 5 (11): : 5801 - 5814
  • [29] Multi-Branch Spatial-Temporal Network for Action Recognition
    Wang, Yingying
    Li, Wei
    Tao, Ran
    IEEE SIGNAL PROCESSING LETTERS, 2019, 26 (10) : 1556 - 1560
  • [30] ON A SPATIAL-TEMPORAL DECOMPOSITION OF OPTICALFLOW
    Patrone, Aniello Raffaele
    Scherzer, Otmar
    INVERSE PROBLEMS AND IMAGING, 2017, 11 (04) : 761 - 781