Fast Learning of Temporal Action Proposal via Dense Boundary Generator

Generating temporal action proposals remains a very challenging problem, where the main issue lies in predicting precise temporal proposal boundaries and reliable action confidence in long and untrimmed real-world videos. In this paper, we propose an efficient and unified framework to generate temporal action proposals named Dense Boundary Generator (DBG), which draws inspiration from boundary-sensitive methods and implements boundary classification and action completeness regression for densely distributed proposals. In particular, the DBG consists of two modules: Temporal boundary classification (TBC) and Action-aware completeness regression (ACR). The TBC aims to provide two temporal boundary confidence maps by low-level two-stream features, while the ACR is designed to generate an action completeness score map by high-level action-aware features. Moreover, we introduce a dual stream BaseNet (DSB) to encode RGB and optical flow information, which helps to capture discriminative boundary and actionness features. Extensive experiments on popular benchmarks ActivityNet-1. 3 and THUMOS14 demonstrate the superiority of DBG over the state-of-the-art proposal generator (e. g. , MGG and BMN).

Authors

• Chuming Lin Tencent YouTu Lab
• Jian Li Tencent Hunyuan
• Yabiao Wang Tencent Youtu Lab
• Ying Tai State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China School of Intelligence Science and Technology, Nanjing University, Suzhou, China
• Donghao Luo Tencent YouTu Lab
• Zhipeng Cui
• Chengjie Wang Tencent Youtu Lab Shanghai Jiao Tong University
• Jilin Li
• Feiyue Huang
• Rongrong Ji Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China

Keywords

No keywords are indexed for this paper.