计算机科学
特征(语言学)
动作(物理)
边界(拓扑)
人工智能
模式识别(心理学)
数学
语言学
量子力学
物理
数学分析
哲学
作者
Qiang Li,Di Liu,Guang Zu,S.H. Li,Hui Sun,Jianzhong Wang
摘要
This paper presents a temporal action detection (TAD) method with multi-granularity feature aggregation and cross-level boundary modeling (MGCBM). Compared with other methods, our proposed approach has the following advantages. First, different from most existing works which only consider the local temporal context, a simple and computationally efficient Multi-Granularity (MG) module is proposed to comprehensively extract video features in instant, local and global temporal granularities. Second, unlike the methods that only employ the information from single feature pyramid level for action boundary regression, a cross-level boundary modeling (CBM) strategy that integrates the relative information from both the same and higher level features is designed to improve the accuracy of boundary prediction. At last, benefiting from the MG module and CBM strategy, our method outperforms other state-of-the-art approaches on five challenging TAD datasets: THUMOS14, MultiTHUMOS, EPIC-KITCHENS-100, ActivityNet-1.3 and HACS. We make our code and pre-trained model publicly available at: https://github.com/MGCBM/TAL-MGCBM .
科研通智能强力驱动
Strongly Powered by AbleSci AI