{"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/cots-collaborative-two-stream-vision-language","title":"COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval","arxiv_id":"2204.07441","date":"2022-04-15","proceeding":"CVPR 2022 1","authors":["Haoyu Lu","Nanyi Fei","Yuqi Huo","Yizhao Gao","Zhiwu Lu","Ji-Rong Wen"],"abstract":"Large-scale single-stream pre-training has shown dramatic performance in image-text retrieval. Regrettably, it faces low inference efficiency due to heavy attention layers. Recently, two-stream methods like CLIP and ALIGN with high inference efficiency have also shown promising performance, however, they only consider instance-level alignment between the two streams (thus there is still room for improvement). To overcome these limitations, we propose a novel COllaborative Two-Stream vision-language pretraining model termed COTS for image-text retrieval by enhancing cross-modal interaction. In addition to instance level alignment via momentum contrastive learning, we leverage two extra levels of cross-modal interactions in our COTS: (1) Token-level interaction - a masked visionlanguage modeling (MVLM) learning objective is devised without using a cross-stream network module, where variational autoencoder is imposed on the visual encoder to generate visual tokens for each image. (2) Task-level interaction - a KL-alignment learning objective is devised between text-to-image and image-to-text retrieval tasks, where the probability distribution per task is computed with the negative queues in momentum contrastive learning. Under a fair comparison setting, our COTS achieves the highest performance among all two-stream methods and comparable performance (but with 10,800X faster in inference) w.r.t. the latest single-stream methods. Importantly, our COTS is also applicable to text-to-video retrieval, yielding new state-ofthe-art on the widely-used MSR-VTT dataset.","url_abs":"https://arxiv.org/abs/2204.07441v2","url_pdf":"https://arxiv.org/pdf/2204.07441v2.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":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"image-to-text","task_name":"Image to text"},{"task_slug":"image-text-retrieval","task_name":"Image-text Retrieval"},{"task_slug":"image-to-text-retrieval","task_name":"Image-to-Text Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"text-to-video-retrieval","task_name":"Text to Video Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-retrieval-on-msr-vtt","task":"Video Retrieval","dataset":"MSR-VTT","model":"COTS","rank_in_archive_order":24,"of":40,"metrics":{"text-to-video Median Rank":"3","text-to-video R@1":"32.1","text-to-video R@10":"70.2","text-to-video R@5":"60.8"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset":"MSR-VTT-1kA","model":"COTS","rank_in_archive_order":45,"of":63,"metrics":{"text-to-video Median Rank":"2","text-to-video R@1":"36.8","text-to-video R@10":"73.2","text-to-video R@5":"63.8"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.07441","atlas_url":"https://app.syntology.ai/?focus=2204.07441","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":"2204.07441"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2204.07441\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2204.07441"},"call":"get_concepts_for_paper(arxiv_id=\"2204.07441\")"}],"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":"c488956d1eb11c382b0c46ed69fbb2c3215d88e5ce8975821702dd1395ce1134","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}