{"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/multimodal-pretraining-for-dense-video","title":"Multimodal Pretraining for Dense Video Captioning","arxiv_id":"2011.11760","date":"2020-11-10","proceeding":"Asian Chapter of the Association for Computational Linguistics 2020","authors":["Gabriel Huang","Bo Pang","Zhenhai Zhu","Clara Rivera","Radu Soricut"],"abstract":"Learning specific hands-on skills such as cooking, car maintenance, and home repairs increasingly happens via instructional videos. The user experience with such videos is known to be improved by meta-information such as time-stamped annotations for the main steps involved. Generating such annotations automatically is challenging, and we describe here two relevant contributions. First, we construct and release a new dense video captioning dataset, Video Timeline Tags (ViTT), featuring a variety of instructional videos together with time-stamped annotations. Second, we explore several multimodal sequence-to-sequence pretraining strategies that leverage large unsupervised datasets of videos and caption-like texts. We pretrain and subsequently finetune dense video captioning models using both YouCook2 and ViTT. We show that such models generalize well and are robust over a wide variety of instructional videos.","url_abs":"https://arxiv.org/abs/2011.11760v1","url_pdf":"https://arxiv.org/pdf/2011.11760v1.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":"multimodal-pretraining-for-dense-video","repo_url":"https://github.com/google-research-datasets/Video-Timeline-Tags-ViTT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"dense-video-captioning","task_name":"Dense Video Captioning"},{"task_slug":"video-captioning","task_name":"Video Captioning"}],"methods":[],"datasets_introduced":[{"slug":"vitt","name":"ViTT","full_name":"Video Timeline Tags"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/dense-video-captioning-on-youcook2","task":"Dense Video Captioning","dataset":"YouCook2","model":"E2vidD6-MASSalign-BiD","rank_in_archive_order":7,"of":7,"metrics":{"ROUGE-L":"39.03"},"uses_additional_data":true},{"leaderboard":"/sota/video-captioning-on-youcook2","task":"Video Captioning","dataset":"YouCook2","model":"E2vidD6-MASSvid-BiD","rank_in_archive_order":6,"of":14,"metrics":{"BLEU-4":"12.04","CIDEr":"1.22","METEOR":"18.32","ROUGE-L":"39.03"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.11760","atlas_url":"https://app.syntology.ai/?focus=2011.11760","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":"2011.11760"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2011.11760\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2011.11760"},"call":"get_concepts_for_paper(arxiv_id=\"2011.11760\")"}],"by_repo":[{"repo":"google-research-datasets/Video-Timeline-Tags-ViTT","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"286a8e161aaafa24f1b7704389c3701b102ffc9b9480f79f465318a0536ab2d5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}