ACCELERATED LOCAL FEATURE EXTRACTION IN A REUSE SCHEME FOR EFFICIENT ACTION RECOGNITION

被引：0
|
作者：
Chen, Jia-Lin [1 ]
Lin, Zhi-Yi [1 ]
Wan, Yi-Chen [1 ]
Chen, Liang-Gee [1 ]
机构：
[1] Natl Taiwan Univ, Grad Inst Elect Engn, DSP IC Design Lab, Taipei, Taiwan
来源：
2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2016年
关键词：
Feature reuse; local feature extraction; partial feature extraction; action recognition; region of interest;
D O I：
暂无
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
In this paper, we propose an accelerated local feature extraction in a reuse scheme for action recognition. Most local features of the previous frame could be reused due to the high correlation between successive frames. Feature extraction is only needed to be applied partially in the current frame. The full-frame features of the current frame are combined by features extracted at different times. Experimental results show that the proposed reuse scheme can achieve comparable performance to full-frame feature extraction while computational effort is reduced significantly.
引用
收藏
页码：296 / 299
页数：4
相关论文
共 50 条
  • [31] A Feature Extraction Method for Human Action Recognition using Body-Worn Inertial Sensors
    Guo, Ming
    Wang, Zhelong
    PROCEEDINGS OF THE 2015 IEEE 19TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN (CSCWD), 2015, : 576 - 581
  • [32] ECG Identity Recognition Based on Feature Reuse Residual Network
    Yang, Zhengqiang
    Liu, Linyue
    Li, Ning
    Tian, Junwei
    PROCESSES, 2022, 10 (04)
  • [33] Efficient Action Recognition with MoFREAK
    Whiten, Chris
    Laganiere, Robert
    Bilodeau, Guillaume-Alexandre
    2013 INTERNATIONAL CONFERENCE ON COMPUTER AND ROBOT VISION (CRV), 2013, : 319 - 325
  • [34] KS-FuseNet: An Efficient Action Recognition Method Based on Keyframe Selection and Feature Fusion
    Mao, Keming
    Xiao, Yilong
    Jing, Xin
    Hu, Zepeng
    Ping, Yi
    PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2024, PT VII, 2025, 15037 : 540 - 553
  • [35] FEATURELESS: BYPASSING FEATURE EXTRACTION IN ACTION CATEGORIZATION
    Pintea, S. L.
    Mettes, P. S.
    van Gemert, J. C.
    Sineulders, A. W. M.
    2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2016, : 196 - 200
  • [36] Trajectory-Set Feature for Action Recognition
    Matsui, Kenji
    Tamaki, Toru
    Raytchev, Bisser
    Kaneda, Kazufumi
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2017, E100D (08) : 1922 - 1924
  • [37] Recurrent Spatiotemporal Feature Learning for Action Recognition
    Chen, Ze
    Lu, Hongtao
    ICRAI 2018: PROCEEDINGS OF 2018 4TH INTERNATIONAL CONFERENCE ON ROBOTICS AND ARTIFICIAL INTELLIGENCE -, 2018, : 12 - 17
  • [38] Spatiotemporal feature enhancement network for action recognition
    Huang, Guancheng
    Wang, Xiuhui
    Li, Xuesheng
    Wang, Yaru
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (19) : 57187 - 57197
  • [39] Action Recognition Based on Feature Interaction and Clustering
    Li K.
    Cai P.
    Zhou Z.
    Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2023, 35 (06): : 903 - 914
  • [40] DEEP SELECTIVE FEATURE LEARNING FOR ACTION RECOGNITION
    Li, Ziqiang
    Ge, Yongxin
    Feng, Jinyuan
    Qi, Xiaolei
    Yu, Jiaruo
    Yu, Hui
    2020 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2020,
12345