{"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/rudder-a-cross-lingual-video-and-text","title":"Rudder: A Cross Lingual Video and Text Retrieval Dataset","arxiv_id":"2103.05457","date":"2021-03-09","proceeding":null,"authors":["Jayaprakash A","abhishek","Rishabh Dabral","Ganesh Ramakrishnan","Preethi Jyothi"],"abstract":"Video retrieval using natural language queries requires learning semantically meaningful joint embeddings between the text and the audio-visual input. Often, such joint embeddings are learnt using pairwise (or triplet) contrastive loss objectives which cannot give enough attention to 'difficult-to-retrieve' samples during training. This problem is especially pronounced in data-scarce settings where the data is relatively small (10% of the large scale MSR-VTT) to cover the rather complex audio-visual embedding space. In this context, we introduce Rudder - a multilingual video-text retrieval dataset that includes audio and textual captions in Marathi, Hindi, Tamil, Kannada, Malayalam and Telugu. Furthermore, we propose to compensate for data scarcity by using domain knowledge to augment supervision. To this end, in addition to the conventional three samples of a triplet (anchor, positive, and negative), we introduce a fourth term - a partial - to define a differential margin based partialorder loss. The partials are heuristically sampled such that they semantically lie in the overlap zone between the positives and the negatives, thereby resulting in broader embedding coverage. Our proposals consistently outperform the conventional max-margin and triplet losses and improve the state-of-the-art on MSR-VTT and DiDeMO datasets. We report benchmark results on Rudder while also observing significant gains using the proposed partial order loss, especially when the language specific retrieval models are jointly trained by availing the cross-lingual alignment across the language-specific datasets.","url_abs":"https://arxiv.org/abs/2103.05457v1","url_pdf":"https://arxiv.org/pdf/2103.05457v1.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":"rudder-a-cross-lingual-video-and-text","repo_url":"https://github.com/nshubham655/RUDDER","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"natural-language-queries","task_name":"Natural Language Queries"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":null,"task_name":"Triplet"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"video-text-retrieval","task_name":"Video-Text Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-retrieval-on-charades-sta","task":"Video Retrieval","dataset":"Charades-STA","model":"PO Loss","rank_in_archive_order":1,"of":1,"metrics":{"text-to-video Mean Rank":"162.3","text-to-video Median Rank":"77","text-to-video R@1":"3.6","text-to-video R@10":"15.9","video-to-text Mean Rank":"164.6","video-to-text Median Rank":"83","video-to-text R@1":"3.2","video-to-text R@10":"14.9"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-didemo","task":"Video Retrieval","dataset":"DiDeMo","model":"PO Loss","rank_in_archive_order":38,"of":40,"metrics":{"text-to-video Mean Rank":"40.2","text-to-video Median Rank":"8","text-to-video R@1":"16.3","text-to-video R@10":"56.5","video-to-text Mean Rank":"39.6","video-to-text Median Rank":"8","video-to-text R@1":"15","video-to-text R@10":"54.9"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-rudder","task":"Video Retrieval","dataset":"RUDDER","model":"PO Loss","rank_in_archive_order":1,"of":1,"metrics":{"text-to-video Mean Rank":"66","text-to-video Median Rank":"153.14","text-to-video R@1":"4.48","text-to-video R@10":"20.02","text-to-video R@5":"13.47","text-to-video R@50":"42.49","video-to-text Mean Rank":"73","video-to-text Median Rank":"151.63","video-to-text R@1":"3.87","video-to-text R@10":"19.09","video-to-text R@5":"12.13"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.05457","atlas_url":"https://app.syntology.ai/?focus=2103.05457","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":"2103.05457"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2103.05457\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2103.05457"},"call":"get_concepts_for_paper(arxiv_id=\"2103.05457\")"}],"by_repo":[{"repo":"nshubham655/RUDDER","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":"a60aef5f7ef9d9d4440fbd73dc6ffc9f486c3761c40416186853d615808467ee","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}