EUVIMEDEUVIMED entdecken
Crossref

Dynamic Spatial Focus for Efficient Compressed Video Action Recognition

Ziwei Zheng, Le Yang, Yulin Wang, Miao Zhang, Lijun He, Gao Huang, Fan Li

IEEE Transactions on Circuits and Systems for Video Technology · 2024-02 · 34 (2) · 695-708

DOI: 10.1109/tcsvt.2023.3287201 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2024-02. Verfasst von Ziwei Zheng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 54-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: National Natural Science Foundation of China, China Post-Doctoral Science Foundation, China National Post-Doctoral Program for Innovative Talents.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent years have witnessed a growing interest in compressed video action recognition due to the rapid growth of online videos. It remarkably reduces the storage by replacing raw videos with sparsely sampled RGB frames and other compressed motion cues (motion vectors and residuals). However, existing compressed video action recognition methods face two main issues: First, the inefficiency caused by the usage of coarse-level information under full resolution, and second, the disturbing due to the noisy dynamics in motion vectors. To address the two issues, this paper proposes a dynamic spatial focus method for efficient compressed video action recognition (CoViFocus). Specifically, we first use a light-weighted two-stream architecture to localize the task-relevant patches for both the RGB frames and motion vectors. Then the selected patch pair will be processed by a high-capacity two-stream deep model for the final prediction. Such a patch selection strategy crops out the irrelevant motion noise in motion vectors, as well as reduces the spatial redundancy of the inputs, leading to the high efficiency of our method in the compressed domain. Moreover, we found that the motion vectors can help our method to address the possibly happened static-issue, which means that the focus patches get stuck at some regions related to static objects rather than target actions, which further improves our method. Extensive results on both the HMDB-51 and UCF-101 datasets demonstrate the effectiveness and efficiency of our method in compressed video action recognition tasks.

Förderung

  • National Natural Science Foundation of China
  • China Post-Doctoral Science Foundation
  • China National Post-Doctoral Program for Innovative Talents
  • Natural Science Basic Research Plan in Shaanxi Province of China

Zitieren

APA

Zheng, Z., Yang, L., Wang, Y., Zhang, M., He, L., Huang, G., & Li, F. (2024). Dynamic Spatial Focus for Efficient Compressed Video Action Recognition. IEEE Transactions on Circuits and Systems for Video Technology, 34(2), 695-708. https://doi.org/10.1109/tcsvt.2023.3287201

Vancouver

Zheng Z, Yang L, Wang Y, Zhang M, He L, Huang G, et al. Dynamic Spatial Focus for Efficient Compressed Video Action Recognition. IEEE Transactions on Circuits and Systems for Video Technology. 2024;34(2):695-708. doi:10.1109/tcsvt.2023.3287201

BibTeX
@article{Zheng2024,
  author = {Zheng, Ziwei and Yang, Le and Wang, Yulin and Zhang, Miao and He, Lijun and Huang, Gao and Li, Fan},
  title = {Dynamic Spatial Focus for Efficient Compressed Video Action Recognition},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2024},
  volume = {34},
  number = {2},
  pages = {695--708},
  doi = {10.1109/tcsvt.2023.3287201}
}
Kostenlos starten →