Movie101v2: Improved Movie Narration Benchmark

arXiv:2404.13370v1 Announce Type: new
Abstract: Automatic movie narration targets at creating video-aligned plot descriptions to assist visually impaired audiences. It differs from standard video captioning in that it requires not only describing key visual details but also inferring the plots developed across multiple movie shots, thus posing unique and ongoing challenges. To advance the development of automatic movie narrating systems, we first revisit the limitations of existing datasets and develop a large-scale, bilingual movie narration dataset, Movie101v2. Second, taking into …

abstract advance arxiv benchmark captioning challenges cs.cl cs.cv cs.mm development key movie movıe multiple plot plots standard targets type unique video visual