Expressive Keypoints for Skeleton-based Action Recognition via Skeleton Transformation
This work addresses the challenge of recognizing intricate human actions in skeleton-based recognition, which is important for applications like surveillance and human-computer interaction, though it appears incremental by enhancing existing models with fine-grained details.
The paper tackles the problem of skeleton-based action recognition by proposing Expressive Keypoints that include hand and foot details to capture subtle human actions, achieving state-of-the-art results across seven datasets.
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.