2021/04/07 by Xiang Wang, Shiwei Zhang, Wang, Xiang +9 · 8 citations
Computer Science · #Action (physics) #Artificial intelligence #Artificial neural network #Code (set theory) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Data mining #Discriminative model #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Feature (linguistics) #Human Pose and Action Recognition #Machine learning #Multimodal Machine Learning Applications #Pattern recognition (psychology) #Pretext #Relation (database) #Semi-supervised learning #Set (abstract data type) #Supervised learning #cs.CV
paper · pdf · doi:10.48550/arxiv.2104.03214
published in arXiv (Cornell University) (Cornell University) · Accepted by CVPR-2021
arxiv created 2021/04/07 · openalex publication_date 2021/04/07 · arxiv updated 2021/04/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
Self-supervised learning presents a remarkable performance to utilize unlabeled data for various video tasks. In this paper, we focus on applying the power of self-supervised methods to improve semi-supervised action proposal generation. Particularly, we design an effective Self-supervised Semi-supervised Temporal Action Proposal (SSTAP) framework. The SSTAP contains two crucial branches, i.e., temporal-aware semi-supervised branch and relation-aware self-supervised branch. The semi-supervised branch improves the proposal model by introducing two temporal perturbations, i.e., temporal feature shift and temporal feature flip, in the mean teacher framework. The self-supervised branch defines two pretext tasks, including masked feature reconstruction and clip-order prediction, to learn the relation of temporal clues. By this means, SSTAP can better explore unlabeled videos, and improve the discriminative abilities of learned action features. We extensively evaluate the proposed SSTAP on THUMOS14 and ActivityNet v1.3 datasets. The experimental results demonstrate that SSTAP significantly outperforms state-of-the-art semi-supervised methods and even matches fully-supervised methods. Code is available at https://github.com/wangxiang1230/SSTAP.