Exploiting Auxiliary Caption for Video Grounding

arXiv:2301.05997v3 Announce Type: replace
Abstract: Video grounding aims to locate a moment of interest matching the given query sentence from an untrimmed video. Previous works ignore the {sparsity dilemma} in video annotations, which fails to provide the context information between potential events and query sentences in the dataset. In this paper, we contend that exploiting easily available captions which describe general actions, i.e., auxiliary captions defined in our paper, will significantly boost the performance. To this end, we propose an …

abstract annotations arxiv context cs.cv dataset events information paper query sparsity type video