Effective action recognition with embedded key point shifts

• Main Authors: Cao, Haozhi, Xu, Yuecong, Yang, Jianfei, Mao, Kezhi, Yin, Jianxiong, See, Simon
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Engineering::Electrical and electronic engineering; Action Recognition; Temporal Feature
• Online Access: https://hdl.handle.net/10356/162581
• Institution: Nanyang Technological University

Temporal feature extraction is an essential technique in video-based action recognition. Key points have been utilized in skeleton-based action recognition methods but they require costly key point annotation. In this paper, we propose a novel temporal feature extraction module, named Key Point Shif...