{"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/zoom-better-to-see-clearer-human-and-object","title":"Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net","arxiv_id":"1511.06881","date":"2015-11-21","proceeding":null,"authors":["Fangting Xia","Peng Wang","Liang-Chieh Chen","Alan L. Yuille"],"abstract":"Parsing articulated objects, e.g. humans and animals, into semantic parts\n(e.g. body, head and arms, etc.) from natural images is a challenging and\nfundamental problem for computer vision. A big difficulty is the large\nvariability of scale and location for objects and their corresponding parts.\nEven limited mistakes in estimating scale and location will degrade the parsing\noutput and cause errors in boundary details. To tackle these difficulties, we\npropose a \"Hierarchical Auto-Zoom Net\" (HAZN) for object part parsing which\nadapts to the local scales of objects and parts. HAZN is a sequence of two\n\"Auto-Zoom Net\" (AZNs), each employing fully convolutional networks that\nperform two tasks: (1) predict the locations and scales of object instances\n(the first AZN) or their parts (the second AZN); (2) estimate the part scores\nfor predicted object instance or part regions. Our model can adaptively \"zoom\"\n(resize) predicted image regions into their proper scales to refine the\nparsing.\n  We conduct extensive experiments over the PASCAL part datasets on humans,\nhorses, and cows. For humans, our approach significantly outperforms the\nstate-of-the-arts by 5% mIOU and is especially better at segmenting small\ninstances and small parts. We obtain similar improvements for parsing cows and\nhorses over alternative methods. In summary, our strategy of first zooming into\nobjects and then zooming into parts is very effective. It also enables us to\nprocess different regions of the image at different scales adaptively so that,\nfor example, we do not need to waste computational resources scaling the entire\nimage.","url_abs":"http://arxiv.org/abs/1511.06881v5","url_pdf":"http://arxiv.org/pdf/1511.06881v5.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":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/human-part-segmentation-on-pascal-person-part","task":"Human Part Segmentation","dataset":"PASCAL-Part","model":"HAZN","rank_in_archive_order":7,"of":7,"metrics":{"mIoU":"57.54"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1511.06881","atlas_url":"https://app.syntology.ai/?focus=1511.06881","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":"1511.06881"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1511.06881\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1511.06881"},"call":"get_concepts_for_paper(arxiv_id=\"1511.06881\")"}],"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":"567ca8f71ccc9297277587f30fa681afa105943122b816b4a301aac57631e011","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}