{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/detect-what-you-can-detecting-and","title":"Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts","arxiv_id":"1406.2031","date":"2014-06-08","proceeding":"CVPR 2014 6","authors":["Xianjie Chen","Roozbeh Mottaghi","Xiaobai Liu","Sanja Fidler","Raquel Urtasun","Alan Yuille"],"abstract":"Detecting objects becomes difficult when we need to deal with large shape\ndeformation, occlusion and low resolution. We propose a novel approach to i)\nhandle large deformations and partial occlusions in animals (as examples of\nhighly deformable objects), ii) describe them in terms of body parts, and iii)\ndetect them when their body parts are hard to detect (e.g., animals depicted at\nlow resolution). We represent the holistic object and body parts separately and\nuse a fully connected model to arrange templates for the holistic object and\nbody parts. Our model automatically decouples the holistic object or body parts\nfrom the model when they are hard to detect. This enables us to represent a\nlarge number of holistic object and body part combinations to better deal with\ndifferent \"detectability\" patterns caused by deformations, occlusion and/or low\nresolution.\n  We apply our method to the six animal categories in the PASCAL VOC dataset\nand show that our method significantly improves state-of-the-art (by 4.1% AP)\nand provides a richer representation for objects. During training we use\nannotations for body parts (e.g., head, torso, etc), making use of a new\ndataset of fully annotated object parts for PASCAL VOC 2010, which provides a\nmask for each part.","url_abs":"http://arxiv.org/abs/1406.2031v1","url_pdf":"http://arxiv.org/pdf/1406.2031v1.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":"object","task_name":"Object"},{"task_slug":"semantic-part-detection","task_name":"Semantic Part Detection"}],"methods":[],"datasets_introduced":[{"slug":"pascal-person-part","name":"PASCAL-Part","full_name":"PASCAL-Part"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1406.2031","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}