RPAN: An End-to-End Recurrent Pose-Attention Network for Action Recognition in Videos

• Published in: Proceedings / IEEE International Conference on Computer Vision pp. 3745 - 3754
• Main Authors: Wenbin Du, Yali Wang, Yu Qiao
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2017
• Subjects: Computer vision; Heating systems; Image recognition; Pose estimation; Recurrent neural networks; Robustness; Videos

Recent studies demonstrate the effectiveness of Recurrent Neural Networks (RNNs) for action recognition in videos. However, previous works mainly utilize video-level category as supervision to train RNNs, which may prohibit RNNs to learn complex motion structures along time. In this paper, we propos...