Toward Accurate Person-level Action Recognition in Videos of Crowed Scenes

By Li Yuan, Yichen Zhou, Shuning Chang, Shuning Chang, Ziyuan Huang, Yupeng Chen, Xuecheng Nie, Tao Wang, Jiashi Feng, Shuicheng Yan. 2020

7 citations recorded by the source corpus.

Detecting and recognizing human action in videos with crowed scenes is a challenging problem due to the complex environment and diversity events. Prior works always fail to deal with this problem in two aspects: (1) lacking utilizing information of the scenes; (2) lacking training data in the crowd and complex scenes. In this paper, we focus on improving spatio-temporal action recognition by fully-utilizing the information of scenes and collecting new data. A top-down strategy is used to overcome the limitations. Specifically, we adopt a strong human detector to detect the spatial location of each frame. We then apply action recognition models to learn the spatio-temporal information from video frames on both the HIE dataset and new data with diverse scenes from the internet, which can improve the generalization ability of our model. Besides, the scenes information is extracted by the semantic segmentation model to assistant the process. As a result, our method achieved an average 26.05 wf\_mAP (ranking 1st place in the ACM MM grand challenge 2020: Human in Events).

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jiashi Feng
2. Shuicheng Yan
3. Weihao Yu
4. Li Yuan
5. Yujun Shi
6. Francis E. H. Tay
7. Yunpeng Chen
8. Dacheng Tao

In Computer Vision and Pattern Recognition

1. Jiashi Feng
2. Shuicheng Yan
3. Dacheng Tao
4. Weihao Yu
5. Li Yuan
6. Yunpeng Chen
7. Luc Van Gool
8. Yujun Shi

Citations in the corpus

• VOLO: Vision Outlooker for Visual Recognition (2021, neutral): “vision task [22], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], [41].”
• Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet (2021, methodology): “Self-attention in CNNs Self-attention mechanism has been widely applied to CNNs in vision task [38, 57, 19, 47, 20, 39, 1, 6, 18, 31, 42, 13, 50, 48].”