Journal
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
Volume 15, Issue 3, Pages -Publisher
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3321511
Keywords
Visual attention; action-relevant key volume; variance-based scheme; human action recognition
Categories
Funding
- National Natural Science Foundation of China [61673402, 61273270, 60802069]
- Natural Science Foundation of Guangdong [2017A030311029]
- National Key R&D Program of China [2018YFB1601101]
- Science and Technology Program of Guangzhou [201704020180]
- Fundamental Research Funds for the Central Universities of China [17lgzd08]
Ask authors/readers for more resources
Recently, many deep learning approaches have shown remarkable progress on human action recognition. However, it remains unclear how to extract the useful information in videos since only video-level labels are available in the training phase. To address this limitation, many efforts have been made to improve the performance of action recognition by applying the visual attention mechanism in the deep learning model. In this article, we propose a novel deep model called Moving Foreground Attention (MFA) that enhances the performance of action recognition by guiding the model to focus on the discriminative foreground targets. In our work, MFA detects the moving foreground through a proposed variance-based algorithm. Meanwhile, an unsupervised proposal is utilized to mine the action-related key volumes and generate corresponding correlation scores. Based on these scores, a newly proposed stochastic-out scheme is exploited to train the MFA. Experiment results show that action recognition performance can be significantly improved by using our proposed techniques, and our model achieves state-of-the-art performance on UCF101 and HMDB51.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available