{"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/taco-token-aware-cascade-contrastive-learning","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","arxiv_id":"2108.09980","date":"2021-08-23","proceeding":"ICCV 2021 10","authors":["Jianwei Yang","Yonatan Bisk","Jianfeng Gao"],"abstract":"Contrastive learning has been widely used to train transformer-based vision-language models for video-text alignment and multi-modal representation learning. This paper presents a new algorithm called Token-Aware Cascade contrastive learning (TACo) that improves contrastive learning using two novel techniques. The first is the token-aware contrastive loss which is computed by taking into account the syntactic classes of words. This is motivated by the observation that for a video-text pair, the content words in the text, such as nouns and verbs, are more likely to be aligned with the visual contents in the video than the function words. Second, a cascade sampling method is applied to generate a small set of hard negative examples for efficient loss estimation for multi-modal fusion layers. To validate the effectiveness of TACo, in our experiments we finetune pretrained models for a set of downstream tasks including text-video retrieval (YouCook2, MSR-VTT and ActivityNet), video action step localization (CrossTask), video action segmentation (COIN). The results show that our models attain consistent improvements across different experimental settings over previous methods, setting new state-of-the-art on three public text-video retrieval benchmarks of YouCook2, MSR-VTT and ActivityNet.","url_abs":"https://arxiv.org/abs/2108.09980v1","url_pdf":"https://arxiv.org/pdf/2108.09980v1.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":[],"tasks":[{"task_slug":"action-segmentation","task_name":"Action Segmentation"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"zero-shot-video-retrieval","task_name":"Zero-Shot Video Retrieval"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-segmentation-on-coin","task":"Action Segmentation","dataset":"COIN","model":"TACo","rank_in_archive_order":6,"of":9,"metrics":{"Frame accuracy":"68.4"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-crosstask","task":"Temporal Action Localization","dataset":"CrossTask","model":"TACo","rank_in_archive_order":3,"of":7,"metrics":{"Recall":"42.5"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-activitynet","task":"Video Retrieval","dataset":"ActivityNet","model":"TACo","rank_in_archive_order":26,"of":31,"metrics":{"text-to-video Median Rank":"3.0","text-to-video R@1":"30.4","text-to-video R@5":"61.2","text-to-video R@50":"93.4"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-msr-vtt","task":"Video Retrieval","dataset":"MSR-VTT","model":"TACo","rank_in_archive_order":30,"of":40,"metrics":{"text-to-video Median Rank":"5","text-to-video R@1":"24.8","text-to-video R@10":"64.0","text-to-video R@5":"52.1"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset":"MSR-VTT-1kA","model":"TACo","rank_in_archive_order":51,"of":63,"metrics":{"text-to-video Median Rank":"4","text-to-video R@1":"28.4","text-to-video R@10":"71.2","text-to-video R@5":"57.8"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-youcook2","task":"Video Retrieval","dataset":"YouCook2","model":"TACo","rank_in_archive_order":5,"of":16,"metrics":{"text-to-video Median Rank":"4","text-to-video R@1":"29.6","text-to-video R@10":"72.7","text-to-video R@5":"59.7"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-video-retrieval-on-msr-vtt","task":"Zero-Shot Video Retrieval","dataset":"MSR-VTT","model":"TACo","rank_in_archive_order":38,"of":41,"metrics":{"text-to-video R@1":"9.8","text-to-video R@10":"33.4","text-to-video R@5":"25.0"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-retrieval-on-youcook2","task":"Zero-Shot Video Retrieval","dataset":"YouCook2","model":"TACo","rank_in_archive_order":5,"of":9,"metrics":{"text-to-video Mean Rank":"8","text-to-video R@1":"19.9","text-to-video R@10":"55.7","text-to-video R@5":"43.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2108.09980","atlas_url":"https://app.syntology.ai/?focus=2108.09980","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":"2108.09980"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2108.09980\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2108.09980"},"call":"get_concepts_for_paper(arxiv_id=\"2108.09980\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"bbd8d1d06d1d08896aa2f37213921c4404676710c6a62e3df1210cd5b2aeaa24","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}