{"url":"/task/live-video-captioning","name":"Live Video Captioning","slug":"live-video-captioning","description_markdown":"Live video captioning (LVC) involves detecting and describing dense events within video streams. Traditional dense video captioning approaches typically focus on offline solutions where the entire video is available for analysis by the captioning model. In contrast, the LVC paradigm requires models to generate captions for video streams in an online manner. This imposes significant constraints, such as working with incomplete observations of the video and the need for temporal anticipation.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2,"papers_with_code":2,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/live-video-captioning-on-activitynet-captions","slug":"live-video-captioning-on-activitynet-captions","dataset":"ActivityNet Captions","dataset_url":"/dataset/activitynet-captions","rows_in_archive":1,"metrics":["Live Score"],"first_row_in_archive_order":{"model":"LVC","paper_title":"Live Video Captioning","paper_url":"/paper/live-video-captioning","paper_date":"2024-06-20","arxiv_id":"2406.14206","code_links":[{"title":"gramuah/lvc","url":"https://github.com/gramuah/lvc"}],"syntology":null}}],"datasets":[{"url":"/dataset/activitynet-captions","name":"ActivityNet Captions","full_name":"","num_papers_in_archive":255}],"subtasks":[],"parent_tasks":[{"url":"/task/dense-captioning","name":"Dense Captioning"},{"url":"/task/video-captioning","name":"Video Captioning"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":2,"of":2,"tagged_in_all":2,"items":[{"url":"/paper/live-video-captioning","title":"Live Video Captioning","date":"2024-06-20","arxiv_id":"2406.14206","repositories_listed":1,"syntology":null},{"url":"/paper/streaming-dense-video-captioning","title":"Streaming Dense Video Captioning","date":"2024-04-01","arxiv_id":"2404.01297","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}