An Action Recognition Method Based on Deformable Convolution Network

被引：0
|
作者：
Dong, Xu [1 ]
Tan, Li [1 ]
Zhou, Lina [1 ]
Song, Yanyan [1 ]
机构：
[1] Beijing Technol & Business Univ, Sch Comp & Informat Engn, Beijing, Peoples R China
来源：
2020 4TH INTERNATIONAL CONFERENCE ON CONTROL ENGINEERING AND ARTIFICIAL INTELLIGENCE (CCEAI 2020) | 2020年 / 1487卷
基金：
北京市自然科学基金; 中国国家自然科学基金;
关键词：
SHOT BOUNDARY DETECTION;
D O I：
10.1088/1742-6596/1487/1/012033
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In order to solve the problem of behavior recognition in short video, this paper first proposes a key frame extraction algorithm based on mutual information entropy, which uses sliding window to preserve the timing information between frames. Based on the key frame extraction, a based on Deform-GoogLeNet, a two-stream CNN method for deformable convolutional networks, uses the two-stream network to extract the RGB features and optical Flow characteristics of the image separately, and uses the weighted average method to obtain the results of behavior recognition. On the public dataset Charades dataset, mAP is 22.9, which is higher than the similar fusion algorithm, which proves that the proposed algorithm has a good effect in short video behavior recognition.
引用
收藏
页数：7
相关论文
共 50 条
  • [31] Self-Relational Graph Convolution Network for Skeleton-Based Action Recognition
    Yussif, Sophyani Banaamwini
    Xie, Ning
    Yang, Yang
    Shen, Heng Tao
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 27 - 36
  • [32] LIFRNet: A Novel Lightweight Individual Fish Recognition Method Based on Deformable Convolution and Edge Feature Learning
    Yin, Jianhao
    Wu, Junfeng
    Gao, Chunqi
    Jiang, Zhongai
    AGRICULTURE-BASEL, 2022, 12 (12):
  • [33] Improved AlexNet Based Recognition Algorithm for Deformable Convolution Skin Lesions
    Li H.
    Ma Y.
    Li H.
    Guo L.
    Li H.
    Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology, 2022, 42 (03): : 297 - 303
  • [34] A Reconfigurable Hardware Architecture for Graph Convolution Network in Action Recognition
    Tsai, Tsung-Han
    Chen, Tzu-Chieh
    2023 ASIA PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE, APSIPA ASC, 2023, : 1075 - 1078
  • [35] MCANet: a lightweight action recognition network with multidimensional convolution and attention
    Tian, Qiuhong
    Miao, Weilun
    Zhang, Lizao
    Yang, Ziyu
    Yu, Yang
    Zhao, Yanying
    Yao, Lan
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2024,
  • [36] Modulation recognition method based on multi-inputs convolution neural network
    Zha X.
    Peng H.
    Qin X.
    Li G.
    Li T.
    Tongxin Xuebao/Journal on Communications, 2019, 40 (11): : 30 - 37
  • [37] Face Recognition Based on Convolution Neural Network
    Yan, Kewen
    Huang, Shaohui
    Song, Yaoxian
    Liu, Wei
    Fan, Neng
    PROCEEDINGS OF THE 36TH CHINESE CONTROL CONFERENCE (CCC 2017), 2017, : 4077 - 4081
  • [38] Fruit Recognition Based On Convolution Neural Network
    Hou, Lei
    Wu, QingXiang
    Sun, Qiyan
    Yang, Heng
    Li, Pengfei
    2016 12TH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (ICNC-FSKD), 2016, : 18 - 22
  • [39] Taekwondo Action Recognition Method Based on Partial Perception Structure Graph Convolution Framework
    Liang, Jianqiao
    Zuo, Guocai
    SCIENTIFIC PROGRAMMING, 2022, 2022
  • [40] Multitask Seismic Inversion Based on Deformable Convolution and Generative Adversarial Network
    Luo, Yanyan
    Liu, Xudong
    Meng, He
    Ye, Yueming
    Wu, Bangyu
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2024, 21 : 1 - 5
12345