{"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/vindlu-a-recipe-for-effective-video-and","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","arxiv_id":"2212.05051","date":"2022-12-09","proceeding":"CVPR 2023 1","authors":["Feng Cheng","Xizi Wang","Jie Lei","David Crandall","Mohit Bansal","Gedas Bertasius"],"abstract":"The last several years have witnessed remarkable progress in video-and-language (VidL) understanding. However, most modern VidL approaches use complex and specialized model architectures and sophisticated pretraining protocols, making the reproducibility, analysis and comparisons of these frameworks difficult. Hence, instead of proposing yet another new VidL model, this paper conducts a thorough empirical study demystifying the most important factors in the VidL model design. Among the factors that we investigate are (i) the spatiotemporal architecture design, (ii) the multimodal fusion schemes, (iii) the pretraining objectives, (iv) the choice of pretraining data, (v) pretraining and finetuning protocols, and (vi) dataset and model scaling. Our empirical study reveals that the most important design factors include: temporal modeling, video-to-text multimodal fusion, masked modeling objectives, and joint training on images and videos. Using these empirical insights, we then develop a step-by-step recipe, dubbed VindLU, for effective VidL pretraining. Our final model trained using our recipe achieves comparable or better than state-of-the-art results on several VidL tasks without relying on external CLIP pretraining. In particular, on the text-to-video retrieval task, our approach obtains 61.2% on DiDeMo, and 55.0% on ActivityNet, outperforming current SOTA by 7.8% and 6.1% respectively. Furthermore, our model also obtains state-of-the-art video question-answering results on ActivityNet-QA, MSRVTT-QA, MSRVTT-MC and TVQA. Our code and pretrained models are publicly available at: https://github.com/klauscc/VindLU.","url_abs":"https://arxiv.org/abs/2212.05051v2","url_pdf":"https://arxiv.org/pdf/2212.05051v2.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":"vindlu-a-recipe-for-effective-video-and","repo_url":"https://github.com/klauscc/vindlu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-to-video-retrieval","task_name":"Text to Video Retrieval"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-activitynet-qa","task":"Video Question Answering","dataset":"ActivityNet-QA","model":"VindLU","rank_in_archive_order":19,"of":36,"metrics":{"Accuracy":"44.7"},"uses_additional_data":true},{"leaderboard":"/sota/video-question-answering-on-msrvtt-mc","task":"Video Question Answering","dataset":"MSRVTT-MC","model":"VindLU","rank_in_archive_order":3,"of":7,"metrics":{"Accuracy":"95.5"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-msrvtt-qa","task":"Video Question Answering","dataset":"MSRVTT-QA","model":"VindLU","rank_in_archive_order":10,"of":14,"metrics":{"Accuracy":"44.6"},"uses_additional_data":true},{"leaderboard":"/sota/video-question-answering-on-tvqa","task":"Video Question Answering","dataset":"TVQA","model":"VindLU","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy":"79.0"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-activitynet","task":"Video Retrieval","dataset":"ActivityNet","model":"VindLU","rank_in_archive_order":11,"of":31,"metrics":{"text-to-video R@1":"55.0","text-to-video R@10":" 89.7","text-to-video R@5":" 81.4"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-condensed-movies","task":"Video Retrieval","dataset":"Condensed Movies","model":"VINDLU","rank_in_archive_order":2,"of":3,"metrics":{"text-to-video R@1":"18.4","text-to-video R@10":"44.3","text-to-video R@5":"36.4 "},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-didemo","task":"Video Retrieval","dataset":"DiDeMo","model":"VindLU","rank_in_archive_order":9,"of":40,"metrics":{"text-to-video R@1":"61.2","text-to-video R@10":"91.0","text-to-video R@5":"85.8"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset":"MSR-VTT-1kA","model":"VindLU","rank_in_archive_order":34,"of":63,"metrics":{"text-to-video R@1":"46.5","text-to-video R@10":"80.4","text-to-video R@5":"71.5"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-queryd","task":"Video Retrieval","dataset":"QuerYD","model":"VINDLU","rank_in_archive_order":3,"of":5,"metrics":{"text-to-video R@1":"67.8","text-to-video R@10":"81.8","text-to-video R@5":"86.3"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-ssv2-label-retrieval","task":"Video Retrieval","dataset":"SSv2-label retrieval","model":"VindLU","rank_in_archive_order":4,"of":5,"metrics":{"text-to-video R@1":"53.1","text-to-video R@5":"81.8"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-ssv2-template-retrieval","task":"Video Retrieval","dataset":"SSv2-template retrieval","model":"VindLU","rank_in_archive_order":4,"of":5,"metrics":{"text-to-video R@1":"83.3","text-to-video R@10":"100","text-to-video R@5":"100"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.05051","atlas_url":"https://app.syntology.ai/?focus=2212.05051","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":"2212.05051"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2212.05051\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2212.05051"},"call":"get_concepts_for_paper(arxiv_id=\"2212.05051\")"}],"by_repo":[{"repo":"klauscc/vindlu","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["Cheng_VindLU_A_Recipe_for_Effective_Video-and-Language_Pretraining_CVPR_2023_paper"],"harvested_for_calls":[]}],"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":"34a67da4ceff8003df569215a23d28a5426263ad39442acd553610c58a0ddbd5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}