Joint Feature Optimization and Fusion for Compressed Action Recognition
Recent methods including CoViAR and DMC-Net provide a new paradigm for action recognition since they are directly targeted at compressed videos (e.g., MPEG4 files). It avoids the cumbersome decoding procedure of traditional methods, and leverages the pre-encoded motion vectors and residuals in compr...
Ausführliche Beschreibung
Bibliographische Detailangaben
Veröffentlicht in: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 30(2021) vom: 01., Seite 7926-7937
|
1. Verfasser: |
Li, Hanhui
(VerfasserIn) |
Weitere Verfasser: |
Jiang, Xudong,
Guan, Boliang,
Tan, Raymond Rui Ming,
Wang, Ruomei,
Thalmann, Nadia Magnenat |
Format: | Online-Aufsatz
|
Sprache: | English |
Veröffentlicht: |
2021
|
Zugriff auf das übergeordnete Werk: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|
Schlagworte: | Journal Article |