EUVIMEDEUVIMED entdecken
Crossref

Temporal Dropout for Weakly Supervised Action Localization

Chi Xie, Zikun Zhuang, Shengjie Zhao, Shuang Liang

ACM Transactions on Multimedia Computing, Communications, and Applications · 31.08.2023 · 19 (3) · 1-24

DOI: 10.1145/3567827 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 25.02.2023. Verfasst von Chi Xie und 3 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shanghai, Shanghai Innovation Action Project of Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Weakly supervised action localization is a challenging problem in video understanding and action recognition. Existing models usually formulate the training process as direct classification using video-level supervision. They tend to only locate the most discriminative parts of action instances and produce temporally incomplete detection results. A natural solution for this problem, the adversarial erasing strategy, is to remove such parts from training so that models can attend to complementary parts. Previous works do it in an offline and heuristic way. They adopt a multi-stage pipeline, where discriminative regions are determined and erased under the guidance of detection results from last stage. Such a pipeline can be both ineffective and inefficient, possibly hindering the overall performance. On the contrary, we combine adversarial erasing with dropout mechanism and propose a Temporal Dropout Module that learns where to remove in a data-driven and online manner. This plug-and-play module is trained without iterative stages, which not only simplifies the pipeline but also makes the regularization during training easier and more adaptive. Experiments show that the proposed method outperforms previous erasing-based methods by a large margin. More importantly, it achieves universal improvement when plugged into various direct classification methods and obtains state-of-the-art performance.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Shanghai
  • Shanghai Innovation Action Project of Science and Technology
  • National Key Research and Development Project
  • Shanghai Municipal Science and Technology Major Project
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Xie, C., Zhuang, Z., Zhao, S., & Liang, S. (2023). Temporal Dropout for Weakly Supervised Action Localization. ACM Transactions on Multimedia Computing, Communications, and Applications, 19(3), 1-24. https://doi.org/10.1145/3567827

Vancouver

Xie C, Zhuang Z, Zhao S, Liang S. Temporal Dropout for Weakly Supervised Action Localization. ACM Transactions on Multimedia Computing, Communications, and Applications. 2023;19(3):1-24. doi:10.1145/3567827

BibTeX
@article{Xie2023,
  author = {Xie, Chi and Zhuang, Zikun and Zhao, Shengjie and Liang, Shuang},
  title = {Temporal Dropout for Weakly Supervised Action Localization},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2023},
  volume = {19},
  number = {3},
  pages = {1--24},
  doi = {10.1145/3567827}
}
Kostenlos starten →