Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection
This work addresses the challenge of identifying relevant video segments based on text queries for applications in video search and summarization, representing an incremental advance over prior methods.
The paper tackles the problem of video moment retrieval and highlight detection by introducing a Video Context-aware Keyword Attention module that captures keyword variation within the overall video context, resulting in significant performance improvements on benchmarks like QVHighlights, TVSum, and Charades-STA compared to existing methods.
The goal of video moment retrieval and highlight detection is to identify specific segments and highlights based on a given text query. With the rapid growth of video content and the overlap between these tasks, recent works have addressed both simultaneously. However, they still struggle to fully capture the overall video context, making it challenging to determine which words are most relevant. In this paper, we present a novel Video Context-aware Keyword Attention module that overcomes this limitation by capturing keyword variation within the context of the entire video. To achieve this, we introduce a video context clustering module that provides concise representations of the overall video context, thereby enhancing the understanding of keyword dynamics. Furthermore, we propose a keyword weight detection module with keyword-aware contrastive learning that incorporates keyword information to enhance fine-grained alignment between visual and textual features. Extensive experiments on the QVHighlights, TVSum, and Charades-STA benchmarks demonstrate that our proposed method significantly improves performance in moment retrieval and highlight detection tasks compared to existing approaches. Our code is available at: https://github.com/VisualAIKHU/Keyword-DETR