{"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/looking-at-outfit-to-parse-clothing","title":"Looking at Outfit to Parse Clothing","arxiv_id":"1703.01386","date":"2017-03-04","proceeding":null,"authors":["Pongsate Tangseng","Zhipeng Wu","Kota Yamaguchi"],"abstract":"This paper extends fully-convolutional neural networks (FCN) for the clothing\nparsing problem. Clothing parsing requires higher-level knowledge on clothing\nsemantics and contextual cues to disambiguate fine-grained categories. We\nextend FCN architecture with a side-branch network which we refer outfit\nencoder to predict a consistent set of clothing labels to encourage\ncombinatorial preference, and with conditional random field (CRF) to explicitly\nconsider coherent label assignment to the given image. The empirical results\nusing Fashionista and CFPD datasets show that our model achieves\nstate-of-the-art performance in clothing parsing, without additional\nsupervision during training. We also study the qualitative influence of\nannotation on the current clothing parsing benchmarks, with our Web-based tool\nfor multi-scale pixel-wise annotation and manual refinement effort to the\nFashionista dataset. Finally, we show that the image representation of the\noutfit encoder is useful for dress-up image retrieval application.","url_abs":"http://arxiv.org/abs/1703.01386v1","url_pdf":"http://arxiv.org/pdf/1703.01386v1.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":"looking-at-outfit-to-parse-clothing","repo_url":"https://github.com/AemikaChow/DATASOURCE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"looking-at-outfit-to-parse-clothing","repo_url":"https://github.com/CAPTEteam/annotation-tool-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"looking-at-outfit-to-parse-clothing","repo_url":"https://github.com/Gbrtenorio/Gbrtenorio.github.io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"looking-at-outfit-to-parse-clothing","repo_url":"https://github.com/ReemHal/Browser-Based-Annotator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"looking-at-outfit-to-parse-clothing","repo_url":"https://github.com/TheChalice/Annotator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"looking-at-outfit-to-parse-clothing","repo_url":"https://github.com/hrsma2i/dataset-cfpd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"looking-at-outfit-to-parse-clothing","repo_url":"https://github.com/ken90242/js-segment-annotator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"looking-at-outfit-to-parse-clothing","repo_url":"https://github.com/kyamagu/js-segment-annotator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"looking-at-outfit-to-parse-clothing","repo_url":"https://github.com/mdrs-thiago/mdrs-thiago.github.io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fcn","method_name":"FCN"},{"method_slug":"max-pooling","method_name":"Max Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}