{"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/human-semantic-parsing-for-person-re","title":"Human Semantic Parsing for Person Re-identification","arxiv_id":"1804.00216","date":"2018-03-31","proceeding":"CVPR 2018 6","authors":["Mahdi M. Kalayeh","Emrah Basaran","Muhittin Gokmen","Mustafa E. Kamasak","Mubarak Shah"],"abstract":"Person re-identification is a challenging task mainly due to factors such as\nbackground clutter, pose, illumination and camera point of view variations.\nThese elements hinder the process of extracting robust and discriminative\nrepresentations, hence preventing different identities from being successfully\ndistinguished. To improve the representation learning, usually, local features\nfrom human body parts are extracted. However, the common practice for such a\nprocess has been based on bounding box part detection. In this paper, we\npropose to adopt human semantic parsing which, due to its pixel-level accuracy\nand capability of modeling arbitrary contours, is naturally a better\nalternative. Our proposed SPReID integrates human semantic parsing in person\nre-identification and not only considerably outperforms its counter baseline,\nbut achieves state-of-the-art performance. We also show that by employing a\n\\textit{simple} yet effective training strategy, standard popular deep\nconvolutional architectures such as Inception-V3 and ResNet-152, with no\nmodification, while operating solely on full image, can dramatically outperform\ncurrent state-of-the-art. Our proposed methods improve state-of-the-art person\nre-identification on: Market-1501 by ~17% in mAP and ~6% in rank-1, CUHK03 by\n~4% in rank-1 and DukeMTMC-reID by ~24% in mAP and ~10% in rank-1.","url_abs":"http://arxiv.org/abs/1804.00216v1","url_pdf":"http://arxiv.org/pdf/1804.00216v1.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":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"auxiliary-classifier","method_name":"Auxiliary Classifier"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"inception-v3","method_name":"Inception-v3"},{"method_slug":"inception-v3-module","method_name":"Inception-v3 Module"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"SPreID [kalayeh2018human]","rank_in_archive_order":84,"of":135,"metrics":{"Rank-1":"93.6","mAP":"83.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.00216","atlas_url":"https://app.syntology.ai/?focus=1804.00216","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}