Graph-based Action Recognition

Graph-Based Action Recognition is a methodological framework within computer vision that represents human actions as spatiotemporal graphs, where nodes denote body joints or parts and edges encode their spatial and temporal dependencies, to model articulated human motion for action classification.

282

Publications

33.6K

Citations

936

Authors

304

Institutions

Publications per year

2017–2026

227

Authors

936

  1. HL
    Hanqing Lu

    Chinese Academy of Sciences, China

    8 publications · 4K citations

    8

    h-index

  2. YZ
    Yifan Zhang

    Chinese Academy of Sciences, China

    8 publications · 4K citations

    8

    h-index

  3. JC
    Jian Cheng

    Chinese Academy of Sciences, China

    7 publications · 4K citations

    7

    h-index

  4. LW
    Liang Wang

    Chinese Academy of Sciences, China

    6 publications · 2.1K citations

    6

    h-index

  5. LS
    Lei Shi

    University of Chinese Academy of Sciences, China

    6 publications · 3K citations

    6

    h-index

1–5 of 936

Venues

  1. arXiv (Cornell University)

    Repository · 30 publications · 1.8K citations

    19

    h-index

  2. Pattern Recognition

    14 publications · 652 citations

    14

    h-index

  3. 12

    h-index

  4. IEEE Transactions on Image Processing

    10 publications · 1.2K citations

    10

    h-index

  5. Neurocomputing

    9 publications · 276 citations

    9

    h-index

1–5