Relation-aware Video Reading Comprehension for Temporal Language Grounding
This work addresses the problem of localizing video moments based on natural language queries for applications in video analysis, presenting a novel method that improves accuracy over previous approaches.
The paper tackles temporal language grounding in videos by formulating it as a video reading comprehension task, proposing a Relation-aware Network (RaNet) that achieves state-of-the-art performance on datasets like ActivityNet-Captions, TACoS, and Charades-STA.
Temporal language grounding in videos aims to localize the temporal span relevant to the given query sentence. Previous methods treat it either as a boundary regression task or a span extraction task. This paper will formulate temporal language grounding into video reading comprehension and propose a Relation-aware Network (RaNet) to address it. This framework aims to select a video moment choice from the predefined answer set with the aid of coarse-and-fine choice-query interaction and choice-choice relation construction. A choice-query interactor is proposed to match the visual and textual information simultaneously in sentence-moment and token-moment levels, leading to a coarse-and-fine cross-modal interaction. Moreover, a novel multi-choice relation constructor is introduced by leveraging graph convolution to capture the dependencies among video moment choices for the best choice selection. Extensive experiments on ActivityNet-Captions, TACoS, and Charades-STA demonstrate the effectiveness of our solution. Codes have been available.