{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/streaming-dense-video-captioning","title":"Streaming Dense Video Captioning","arxiv_id":"2404.01297","date":"2024-04-01","proceeding":"CVPR 2024 1","authors":["Xingyi Zhou","Anurag Arnab","Shyamal Buch","Shen Yan","Austin Myers","Xuehan Xiong","Arsha Nagrani","Cordelia Schmid"],"abstract":"An ideal model for dense video captioning -- predicting captions localized temporally in a video -- should be able to handle long input videos, predict rich, detailed textual descriptions, and be able to produce outputs before processing the entire video. Current state-of-the-art models, however, process a fixed number of downsampled frames, and make a single full prediction after seeing the whole video. We propose a streaming dense video captioning model that consists of two novel components: First, we propose a new memory module, based on clustering incoming tokens, which can handle arbitrarily long videos as the memory is of a fixed size. Second, we develop a streaming decoding algorithm that enables our model to make predictions before the entire video has been processed. Our model achieves this streaming ability, and significantly improves the state-of-the-art on three dense video captioning benchmarks: ActivityNet, YouCook2 and ViTT. Our code is released at https://github.com/google-research/scenic.","url_abs":"https://arxiv.org/abs/2404.01297v1","url_pdf":"https://arxiv.org/pdf/2404.01297v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"streaming-dense-video-captioning","repo_url":"https://github.com/google-research/scenic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"dense-video-captioning","task_name":"Dense Video Captioning"},{"task_slug":"live-video-captioning","task_name":"Live Video Captioning"},{"task_slug":"video-captioning","task_name":"Video Captioning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.01297","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}