Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval

arXiv:2404.07610v1 Announce Type: new
Abstract: There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video. Several studies introduce methods by designing dense video captioning as a multitasking problem of event localization and event captioning to consider inter-task relations. However, addressing both tasks using only visual input is challenging due to the lack of semantic content. In this study, we address this by proposing a novel framework …

abstract arxiv attention captioning cs.cv designing event events localization memory modal multitasking research retrieval studies type video