Action recognition with bootstrapping based long-range temporal context attention

Ziming Liu, Guangyu Gao*, A. K. Qin, Tong Wu, Chi Harold Liu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Citations (Scopus)

Abstract

Actions always refer to complex vision variations in a long-range redundant video sequence. Instead of focusing on limited range sequence, i.e. convolution on adjacent frames, in this paper, we proposed an action recognition approach with bootstrapping based long-range temporal context attention. Specifically, due to vision variations of the local region across frames, we target at capturing temporal context by proposing the Temporal Pixels based Parallel-head Attention (TPPA) block. In TPPA, we apply the self-attention mechanism between local regions at the same position across temporal frames to capture the interaction impacts. Meanwhile, to deal with video redundancy and capture long-range context, the TPPA is extended to the Random Frames based Bootstrapping Attention (RFBA) framework. While the bootstrapping sampling frames have the same distribution of the whole video sequence, the RFBA not only captures longer temporal context with only a few sampling frames but also has comprehensive representation through multiple sampling. Furthermore, we also try to apply this temporal context attention to image-based action recognition, by transforming the image into “pseudo video“with the spatial shift. Finally, we conduct extensive experiments and empirical evaluations on two most popular datasets: UCF101 for videos and Stanford40 for images. In particular, our approach achieves top-1 accuracy of 91.7% in UCF101 and mAP of 90.9% in Stanford40.

Original languageEnglish
Title of host publicationMM 2019 - Proceedings of the 27th ACM International Conference on Multimedia
PublisherAssociation for Computing Machinery, Inc
Pages583-591
Number of pages9
ISBN (Electronic)9781450368896
DOIs
Publication statusPublished - 15 Oct 2019
Event27th ACM International Conference on Multimedia, MM 2019 - Nice, France
Duration: 21 Oct 201925 Oct 2019

Publication series

NameMM 2019 - Proceedings of the 27th ACM International Conference on Multimedia

Conference

Conference27th ACM International Conference on Multimedia, MM 2019
Country/TerritoryFrance
CityNice
Period21/10/1925/10/19

Keywords

  • Action recognition
  • Bootstrapping attention
  • Context
  • Self-attention

Fingerprint

Dive into the research topics of 'Action recognition with bootstrapping based long-range temporal context attention'. Together they form a unique fingerprint.

Cite this