{"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/learning-features-by-watching-objects-move","title":"Learning Features by Watching Objects Move","arxiv_id":"1612.06370","date":"2016-12-19","proceeding":"CVPR 2017 7","authors":["Deepak Pathak","Ross Girshick","Piotr Dollár","Trevor Darrell","Bharath Hariharan"],"abstract":"This paper presents a novel yet intuitive approach to unsupervised feature\nlearning. Inspired by the human visual system, we explore whether low-level\nmotion-based grouping cues can be used to learn an effective visual\nrepresentation. Specifically, we use unsupervised motion-based segmentation on\nvideos to obtain segments, which we use as 'pseudo ground truth' to train a\nconvolutional network to segment objects from a single frame. Given the\nextensive evidence that motion plays a key role in the development of the human\nvisual system, we hope that this straightforward approach to unsupervised\nlearning will be more effective than cleverly designed 'pretext' tasks studied\nin the literature. Indeed, our extensive experiments show that this is the\ncase. When used for transfer learning on object detection, our representation\nsignificantly outperforms previous unsupervised approaches across multiple\nsettings, especially when training data for the target task is scarce.","url_abs":"http://arxiv.org/abs/1612.06370v2","url_pdf":"http://arxiv.org/pdf/1612.06370v2.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":"learning-features-by-watching-objects-move","repo_url":"https://github.com/pathak22/unsupervised-video","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"torch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1612.06370","atlas_url":"https://app.syntology.ai/?focus=1612.06370","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":"1612.06370"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1612.06370\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1612.06370"},"call":"get_concepts_for_paper(arxiv_id=\"1612.06370\")"}],"by_repo":[{"repo":"pathak22/unsupervised-video","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":"ccb236632dc0ab987dc3672833d3262abbebb35c8393d0050e6b5117ba935046","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}