UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection
It addresses the need for efficient video content analysis in the era of video explosion, offering a novel joint solution for researchers and practitioners, though it builds on existing component problems.
The paper tackles the joint problem of video moment retrieval and highlight detection by introducing UMT, a unified multi-modal transformer framework that integrates visual-audio learning and treats moment retrieval as keypoint detection, achieving state-of-the-art results on multiple datasets like QVHighlights and Charades-STA.
Finding relevant moments and highlights in videos according to natural language queries is a natural and highly valuable common need in the current video content explosion era. Nevertheless, jointly conducting moment retrieval and highlight detection is an emerging research topic, even though its component problems and some related tasks have already been studied for a while. In this paper, we present the first unified framework, named Unified Multi-modal Transformers (UMT), capable of realizing such joint optimization while can also be easily degenerated for solving individual problems. As far as we are aware, this is the first scheme to integrate multi-modal (visual-audio) learning for either joint optimization or the individual moment retrieval task, and tackles moment retrieval as a keypoint detection problem using a novel query generator and query decoder. Extensive comparisons with existing methods and ablation studies on QVHighlights, Charades-STA, YouTube Highlights, and TVSum datasets demonstrate the effectiveness, superiority, and flexibility of the proposed method under various settings. Source code and pre-trained models are available at https://github.com/TencentARC/UMT.