{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/videoclip-contrastive-pre-training-for-zero","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","arxiv_id":"2109.14084","date":"2021-09-28","proceeding":"EMNLP 2021 11","authors":["Hu Xu","Gargi Ghosh","Po-Yao Huang","Dmytro Okhonko","Armen Aghajanyan","Florian Metze","Luke Zettlemoyer","Christoph Feichtenhofer"],"abstract":"We present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot video and text understanding, without using any labels on downstream tasks. VideoCLIP trains a transformer for video and text by contrasting temporally overlapping positive video-text pairs with hard negatives from nearest neighbor retrieval. Our experiments on a diverse series of downstream tasks, including sequence-level text-video retrieval, VideoQA, token-level action localization, and action segmentation reveal state-of-the-art performance, surpassing prior work, and in some cases even outperforming supervised approaches. Code is made available at https://github.com/pytorch/fairseq/tree/main/examples/MMPT.","url_abs":"https://arxiv.org/abs/2109.14084v2","url_pdf":"https://arxiv.org/pdf/2109.14084v2.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":"videoclip-contrastive-pre-training-for-zero","repo_url":"https://github.com/pytorch/fairseq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"videoclip-contrastive-pre-training-for-zero","repo_url":"https://github.com/facebookresearch/fairseq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"action-segmentation","task_name":"Action Segmentation"},{"task_slug":"long-video-retrieval-background-removed","task_name":"Long Video Retrieval (Background Removed)"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"temporal-relation-extraction","task_name":"Temporal Relation Extraction"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"zero-shot-video-retrieval","task_name":"Zero-Shot Video Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-segmentation-on-coin","task":"Action Segmentation","dataset":"COIN","model":"VideoClip","rank_in_archive_order":4,"of":9,"metrics":{"Frame accuracy":"68.7"},"uses_additional_data":true},{"leaderboard":"/sota/long-video-retrieval-background-removed-on","task":"Long Video Retrieval (Background Removed)","dataset":"YouCook2","model":"VideoCLIP","rank_in_archive_order":3,"of":6,"metrics":{"Cap. Avg. R@1":"74.5","Cap. Avg. R@10":"97.9","Cap. Avg. R@5":"94.5","DTW R@1":"56.0","DTW R@10":"89.9","DTW R@5":"96.3","OTAM R@1":"52.8","OTAM R@10":"89.2","OTAM R@5":"95.0"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-crosstask","task":"Temporal Action Localization","dataset":"CrossTask","model":"VideoCLIP","rank_in_archive_order":1,"of":7,"metrics":{"Recall":"47.3"},"uses_additional_data":true},{"leaderboard":"/sota/temporal-relation-extraction-on-vinoground","task":"Temporal Relation Extraction","dataset":"Vinoground","model":"VideoCLIP","rank_in_archive_order":22,"of":24,"metrics":{"Group Score":"1.2","Text Score":"17","Video Score":"2.8"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset":"MSR-VTT-1kA","model":"VideoCLIP","rank_in_archive_order":50,"of":63,"metrics":{"text-to-video R@1":"30.9","text-to-video R@10":"66.8","text-to-video R@5":"55.4"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-youcook2","task":"Video Retrieval","dataset":"YouCook2","model":"VideoCLIP","rank_in_archive_order":3,"of":16,"metrics":{"text-to-video R@1":"32.2","text-to-video R@10":"75.0","text-to-video R@5":"62.6"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-youcook2","task":"Video Retrieval","dataset":"YouCook2","model":"VideoCLIP (zero-shot)","rank_in_archive_order":8,"of":16,"metrics":{"text-to-video R@1":"22.7","text-to-video R@10":"63.1","text-to-video R@5":"50.4"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-video-retrieval-on-didemo","task":"Zero-Shot Video Retrieval","dataset":"DiDeMo","model":"VideoCLIP","rank_in_archive_order":26,"of":26,"metrics":{"text-to-video R@1":"16.6","text-to-video R@5":"46.9"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-retrieval-on-msr-vtt","task":"Zero-Shot Video Retrieval","dataset":"MSR-VTT","model":"VideoCLIP","rank_in_archive_order":36,"of":41,"metrics":{"text-to-video R@1":"10.4","text-to-video R@10":"30.0","text-to-video R@5":"22.2"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-retrieval-on-youcook2","task":"Zero-Shot Video Retrieval","dataset":"YouCook2","model":"VideoCLIP","rank_in_archive_order":3,"of":9,"metrics":{"text-to-video R@1":"22.7","text-to-video R@10":" 63.1","text-to-video R@5":"50.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.14084","atlas_url":"https://app.syntology.ai/?focus=2109.14084","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2109.14084"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2109.14084\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2109.14084"},"call":"get_concepts_for_paper(arxiv_id=\"2109.14084\")"}],"by_repo":[{"repo":"pytorch/fairseq","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":3,"harvested_for":["2105.08206","2105.14850","2203.09163"],"harvested_for_calls":[{"arxiv_id":"2105.08206","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.08206"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.08206\")"},{"arxiv_id":"2105.14850","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.14850"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.14850\")"},{"arxiv_id":"2203.09163","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.09163"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.09163\")"}]},{"repo":"facebookresearch/fairseq","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b6609b6ca33db1ddb451530e119efad2e505c84e7e952402e094f86ed73e6729","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}