EUVIMEDEUVIMED entdecken
Crossref

Semi-supervised Active Learning for Video Action Detection

Ayush Singh, Aayush J Rana, Akash Kumar, Shruti Vyas, Yogesh Singh Rawat

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (5) · 4891-4899

DOI: 10.1609/aaai.v38i5.28292 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Ayush Singh und 4 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this work, we focus on label efficient learning for video action detection. We develop a novel semi-supervised active learning approach which utilizes both labeled as well as un- labeled data along with informative sample selection for ac- tion detection. Video action detection requires spatio-temporal localization along with classification, which poses several challenges for both active learning (informative sample se- lection) as well as semi-supervised learning (pseudo label generation). First, we propose NoiseAug, a simple augmenta- tion strategy which effectively selects informative samples for video action detection. Next, we propose fft-attention, a novel technique based on high-pass filtering which enables effective utilization of pseudo label for SSL in video action detection by emphasizing on relevant activity region within a video. We evaluate the proposed approach on three different bench- mark datasets, UCF-101-24, JHMDB-21, and Youtube-VOS. First, we demonstrate its effectiveness on video action detec- tion where the proposed approach outperforms prior works in semi-supervised and weakly-supervised learning along with several baseline approaches in both UCF101-24 and JHMDB- 21. Next, we also show its effectiveness on Youtube-VOS for video object segmentation demonstrating its generalization capability for other dense prediction tasks in videos.

Zitieren

APA

Singh, A., Rana, A. J., Kumar, A., Vyas, S., & Rawat, Y. S. (2024). Semi-supervised Active Learning for Video Action Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 38(5), 4891-4899. https://doi.org/10.1609/aaai.v38i5.28292

Vancouver

Singh A, Rana AJ, Kumar A, Vyas S, Rawat YS. Semi-supervised Active Learning for Video Action Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(5):4891-4899. doi:10.1609/aaai.v38i5.28292

BibTeX
@article{Singh2024,
  author = {Singh, Ayush and Rana, Aayush J and Kumar, Akash and Vyas, Shruti and Rawat, Yogesh Singh},
  title = {Semi-supervised Active Learning for Video Action Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {5},
  pages = {4891--4899},
  doi = {10.1609/aaai.v38i5.28292}
}
Kostenlos starten →