Static Image Action Recognition with Hallucinated Fine-Grained Motion Information

Shengyuan Huang, Xing Zhao, Li Niu, Liqing Zhang

Abstract

Static image action recognition is a challenging task due to the lack of motion information in a static image. Some previous works have attempted to hallucinate the motion information in a static image using a generator learnt from freely available unlabeled videos. However, their hallucinated motion information is either low-level or coarse-grained, which may contain lots of noise or lose motion details. In contrast, we propose to hallucinate fine-grained high-level motion information, which is more robust and detail-preserving. Specifically, we hallucinate motion feature map which encodes the motion details of human body parts. We also hallucinate motion attention map to focus on motion-related regions. Our hallucinated motion information can greatly facilitate static image action recognition, which is confirmed by the experiments on two static action image datasets and two video datasets.
BibTeX
@inproceedings{huang2021static,
  author = {Shengyuan Huang and Xing Zhao and Li Niu and Liqing Zhang},
  title = {{Static Image Action Recognition with Hallucinated Fine-Grained Motion Information}},
  booktitle = {ICME},
  year = {2021},
  doi = {10.1109/icme51207.2021.9428245},
}

Loading related content...

Figure