论文标题
提交通用事件边界检测挑战@CVPR 2022：本地上下文建模和全局边界解码方法
Submission to Generic Event Boundary Detection Challenge@CVPR 2022: Local Context Modeling and Global Boundary Decoding Approach
论文作者
论文摘要
通用事件边界检测（GEBD）是视频理解中的一项重要但艰巨的任务，该任务旨在检测人类自然感知事件边界的时刻。在本文中，我们为GEBD任务提供了本地上下文建模和全局边界解码方法。提出了局部上下文建模子网络来感知通用事件边界的各种模式，并产生强大的视频表示和可靠的边界信心。基于它们，全局边界解码子网络被利用从全局视图解码事件边界。我们提出的方法在动力学-GEBD测试集上达到了85.13％的F1得分，与基线方法相比，它实现了22％以上的F1得分提升。该代码可从https://github.com/jackytown/gebd_challenge_cvpr2022获得。
Generic event boundary detection (GEBD) is an important yet challenging task in video understanding, which aims at detecting the moments where humans naturally perceive event boundaries. In this paper, we present a local context modeling and global boundary decoding approach for GEBD task. Local context modeling sub-network is proposed to perceive diverse patterns of generic event boundaries, and it generates powerful video representations and reliable boundary confidence. Based on them, global boundary decoding sub-network is exploited to decode event boundaries from a global view. Our proposed method achieves 85.13% F1-score on Kinetics-GEBD testing set, which achieves a more than 22% F1-score boost compared to the baseline method. The code is available at https://github.com/JackyTown/GEBD_Challenge_CVPR2022.
