{"url":"/task/video-to-text-retrieval","name":"Video to Text Retrieval","slug":"video-to-text-retrieval","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":13,"papers_with_code":9,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/sakuga-42m","name":"Sakuga-42M","full_name":"","num_papers_in_archive":2},{"url":"/dataset/msvd-indonesian","name":"MSVD-Indonesian","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":9,"of":9,"tagged_in_all":13,"items":[{"url":"/paper/learning-a-text-video-embedding-from","title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data","date":"2018-04-07","arxiv_id":"1804.02516","repositories_listed":5,"syntology":null},{"url":"/paper/bridgeformer-bridging-video-text-retrieval","title":"Bridging Video-text Retrieval with Multiple Choice Questions","date":"2022-01-13","arxiv_id":"2201.04850","repositories_listed":2,"syntology":{"n":24,"n_ran":13,"n_unverified":11,"n_pointer_only":6}},{"url":"/paper/2408-02272","title":"COM Kitchens: An Unedited Overhead-view Video Dataset as a Vision-Language Benchmark","date":"2024-08-05","arxiv_id":"2408.02272","repositories_listed":1,"syntology":null},{"url":"/paper/signclip-connecting-text-and-sign-language-by","title":"SignCLIP: Connecting Text and Sign Language by Contrastive Learning","date":"2024-07-01","arxiv_id":"2407.01264","repositories_listed":1,"syntology":null},{"url":"/paper/prototype-based-aleatoric-uncertainty-1","title":"Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval","date":"2023-09-29","arxiv_id":"2309.17093","repositories_listed":1,"syntology":{"n":19,"n_ran":12,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/msvd-indonesian-a-benchmark-for-multimodal","title":"MSVD-Indonesian: A Benchmark for Multimodal Video-Text Tasks in Indonesian","date":"2023-06-20","arxiv_id":"2306.11341","repositories_listed":1,"syntology":null},{"url":"/paper/miles-visual-bert-pre-training-with-injected","title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","date":"2022-04-26","arxiv_id":"2204.12408","repositories_listed":1,"syntology":null},{"url":"/paper/socratic-models-composing-zero-shot","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","date":"2022-04-01","arxiv_id":"2204.00598","repositories_listed":1,"syntology":null},{"url":"/paper/clip2video-mastering-video-text-retrieval-via","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","date":"2021-06-21","arxiv_id":"2106.11097","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}],"syntology_records":3,"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"}}