2020/06/28 by Ceyuan Yang, Yang, Ceyuan, Yinghao Xu +5 · 2 citations
Computer Science · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Human Pose and Action Recognition
paper · pdf · doi:10.48550/arxiv.2006.15489
openalex publication_date 2020/06/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Visual tempo, which describes how fast an action goes, has shown its potential in supervised action recognition. In this work, we demonstrate that visual tempo can also serve as a self-supervision signal for video representation learning. We propose to maximize the mutual information between representations of slow and fast videos via hierarchical contrastive learning (VTHCL). Specifically, by sampling the same instance at slow and fast frame rates respectively, we can obtain slow and fast video frames which share the same semantics but contain different visual tempos. Video representations learned from VTHCL achieve the competitive performances under the self-supervision evaluation protocol for action recognition on UCF-101 (82.1%) and HMDB-51 (49.2%). Moreover, comprehensive experiments suggest that the learned representations are generalized well to other downstream tasks including action detection on AVA and action anticipation on Epic-Kitchen. Finally, we propose Instance Correspondence Map (ICM) to visualize the shared semantics captured by contrastive learning.