MDNet: Motion Distinction Network for Effective Action Recognition

Rongrong Ji, Weirong Ye, Xiao Wang, Yan Yan, Hanzi Wang

Abstract

Motion information is critical for action recognition. Most existing methods perform motion enhancement only from the channel or spatiotemporal dimension. They may fail to achieve fine-grained motion modeling, leading to suboptimal performance. In this paper, we propose a novel motion distinction network (MDNet) to address this challenging problem. Specifically, we first propose a channel-wise motion enhancement (CME) module, which aims to emphasize motion-related channels by leveraging a channel-wise gating mechanism. Then, we propose a cascaded spatiotemporal enhancement (CSTE) module to enhance motion features along the spatiotemporal dimension. Moreover, we design a multi-attention fusion strategy to further refine the enhanced motion features in a moderate manner, enabling the network to focus on discriminative motion regions. The proposed two modules and fusion strategy are complementary for fine-grained motion enhancement. Extensive experiments are conducted on the challenging Something-Something V1 and Kinetics-400 datasets to show the effectiveness of the proposed MDNet.
BibTeX
@inproceedings{ji2022mdnet,
  author = {Rongrong Ji and Weirong Ye and Xiao Wang and Yan Yan and Hanzi Wang},
  title = {{MDNet: Motion Distinction Network for Effective Action Recognition}},
  booktitle = {ICIP},
  year = {2022},
  doi = {10.1109/icip46576.2022.9897291},
}

Loading related content...

Figure