{"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/fashion-landmark-detection-in-the-wild","title":"Fashion Landmark Detection in the Wild","arxiv_id":"1608.03049","date":"2016-08-10","proceeding":null,"authors":["Ziwei Liu","Sijie Yan","Ping Luo","Xiaogang Wang","Xiaoou Tang"],"abstract":"Visual fashion analysis has attracted many attentions in the recent years.\nPrevious work represented clothing regions by either bounding boxes or human\njoints. This work presents fashion landmark detection or fashion alignment,\nwhich is to predict the positions of functional key points defined on the\nfashion items, such as the corners of neckline, hemline, and cuff. To encourage\nfuture studies, we introduce a fashion landmark dataset with over 120K images,\nwhere each image is labeled with eight landmarks. With this dataset, we study\nfashion alignment by cascading multiple convolutional neural networks in three\nstages. These stages gradually improve the accuracies of landmark predictions.\nExtensive experiments demonstrate the effectiveness of the proposed method, as\nwell as its generalization ability to pose estimation. Fashion landmark is also\ncompared to clothing bounding boxes and human joints in two applications,\nfashion attribute prediction and clothes retrieval, showing that fashion\nlandmark is a more discriminative representation to understand fashion images.","url_abs":"http://arxiv.org/abs/1608.03049v1","url_pdf":"http://arxiv.org/pdf/1608.03049v1.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":"fashion-landmark-detection-in-the-wild","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":"fashion-landmark-detection-in-the-wild","repo_url":"https://github.com/fdjingyuan/Deep-Fashion-Analysis-ECCV2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fashion-landmark-detection-in-the-wild","repo_url":"https://github.com/liuziwei7/fashion-landmarks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"fashion-landmark-detection-in-the-wild","repo_url":"https://github.com/shumming/GLE_FLD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1608.03049","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}