{"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/face-recognition-using-deep-multi-pose","title":"Face Recognition Using Deep Multi-Pose Representations","arxiv_id":"1603.07388","date":"2016-03-23","proceeding":null,"authors":["Wael Abd-Almageed","Yue Wua","Stephen Rawlsa","Shai Harel","Tal Hassner","Iacopo Masi","Jongmoo Choi","Jatuporn Toy Leksut","Jungyeon Kim","Prem Natarajan","Ram Nevatia","Gerard Medioni"],"abstract":"We introduce our method and system for face recognition using multiple\npose-aware deep learning models. In our representation, a face image is\nprocessed by several pose-specific deep convolutional neural network (CNN)\nmodels to generate multiple pose-specific features. 3D rendering is used to\ngenerate multiple face poses from the input image. Sensitivity of the\nrecognition system to pose variations is reduced since we use an ensemble of\npose-specific CNN features. The paper presents extensive experimental results\non the effect of landmark detection, CNN layer selection and pose model\nselection on the performance of the recognition pipeline. Our novel\nrepresentation achieves better results than the state-of-the-art on IARPA's CS2\nand NIST's IJB-A in both verification and identification (i.e. search) tasks.","url_abs":"http://arxiv.org/abs/1603.07388v1","url_pdf":"http://arxiv.org/pdf/1603.07388v1.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":"face-recognition","task_name":"Face Recognition"},{"task_slug":"face-verification","task_name":"Face Verification"},{"task_slug":"model-selection","task_name":"Model Selection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-verification-on-ijb-a","task":"Face Verification","dataset":"IJB-A","model":"Deep multi-pose representations","rank_in_archive_order":15,"of":17,"metrics":{"TAR @ FAR=0.01":"78.70%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.07388","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}