Document detail
ID
oai:arXiv.org:2406.18011
Topic
Computer Science - Computer Vision...Author
Yang, Yijie Zhang, Jinlu Zhang, Jiaxu Tu, ZhigangCategory
Computer Science
Year
2024
listing date
7/3/2024
Keywords
skeleton-based action expressive recognition keypointsAbstract
In the realm of skeleton-based action recognition, the traditional methods which rely on coarse body keypoints fall short of capturing subtle human actions.
In this work, we propose Expressive Keypoints that incorporates hand and foot details to form a fine-grained skeletal representation, improving the discriminative ability for existing models in discerning intricate actions.
To efficiently model Expressive Keypoints, the Skeleton Transformation strategy is presented to gradually downsample the keypoints and prioritize prominent joints by allocating the importance weights.
Additionally, a plug-and-play Instance Pooling module is exploited to extend our approach to multi-person scenarios without surging computation costs.
Extensive experimental results over seven datasets present the superiority of our method compared to the state-of-the-art for skeleton-based human action recognition.
Code is available at https://github.com/YijieYang23/SkeleT-GCN.
Yang, Yijie,Zhang, Jinlu,Zhang, Jiaxu,Tu, Zhigang, 2024, Expressive Keypoints for Skeleton-based Action Recognition via Skeleton Transformation
Estimating the cost of visiting hospital outpatient
centre paid study medical hospital cost monash average
