{"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/discover-and-learn-new-objects-from","title":"Discover and Learn New Objects from Documentaries","arxiv_id":"1707.09593","date":"2017-07-30","proceeding":"CVPR 2017 7","authors":["Kai Chen","Hang Song","Chen Change Loy","Dahua Lin"],"abstract":"Despite the remarkable progress in recent years, detecting objects in a new\ncontext remains a challenging task. Detectors learned from a public dataset can\nonly work with a fixed list of categories, while training from scratch usually\nrequires a large amount of training data with detailed annotations. This work\naims to explore a novel approach -- learning object detectors from documentary\nfilms in a weakly supervised manner. This is inspired by the observation that\ndocumentaries often provide dedicated exposition of certain object categories,\nwhere visual presentations are aligned with subtitles. We believe that object\ndetectors can be learned from such a rich source of information. Towards this\ngoal, we develop a joint probabilistic framework, where individual pieces of\ninformation, including video frames and subtitles, are brought together via\nboth visual and linguistic links. On top of this formulation, we further derive\na weakly supervised learning algorithm, where object model learning and\ntraining set mining are unified in an optimization procedure. Experimental\nresults on a real world dataset demonstrate that this is an effective approach\nto learning new object detectors.","url_abs":"http://arxiv.org/abs/1707.09593v1","url_pdf":"http://arxiv.org/pdf/1707.09593v1.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":"discover-and-learn-new-objects-from","repo_url":"https://github.com/hellock/documentary-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[],"datasets_introduced":[{"slug":"wld","name":"WLD","full_name":"WildLife Documentary"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1707.09593","atlas_url":"https://app.syntology.ai/?focus=1707.09593","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":"1707.09593"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1707.09593\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1707.09593"},"call":"get_concepts_for_paper(arxiv_id=\"1707.09593\")"}],"by_repo":[{"repo":"hellock/documentary-learning","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":"1aed384cc10ad34edcd5a486be4646f4b5d75a8f996e2b9e558ce395b353c9f8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}