{"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/deep-perceptual-mapping-for-cross-modal-face","title":"Deep Perceptual Mapping for Cross-Modal Face Recognition","arxiv_id":"1601.05347","date":"2016-01-20","proceeding":null,"authors":["M. Saquib Sarfraz","Rainer Stiefelhagen"],"abstract":"Cross modal face matching between the thermal and visible spectrum is a much\ndesired capability for night-time surveillance and security applications. Due\nto a very large modality gap, thermal-to-visible face recognition is one of the\nmost challenging face matching problem. In this paper, we present an approach\nto bridge this modality gap by a significant margin. Our approach captures the\nhighly non-linear relationship between the two modalities by using a deep\nneural network. Our model attempts to learn a non-linear mapping from visible\nto thermal spectrum while preserving the identity information. We show\nsubstantive performance improvement on three difficult thermal-visible face\ndatasets. The presented approach improves the state-of-the-art by more than\n10\\% on UND-X1 dataset and by more than 15-30\\% on NVESD dataset in terms of\nRank-1 identification. Our method bridges the drop in performance due to the\nmodality gap by more than 40\\%.","url_abs":"http://arxiv.org/abs/1601.05347v2","url_pdf":"http://arxiv.org/pdf/1601.05347v2.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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-recognition-on-carl","task":"Face Recognition","dataset":"Carl","model":"DPM","rank_in_archive_order":2,"of":2,"metrics":{"Rank-1":"71"},"uses_additional_data":false},{"leaderboard":"/sota/face-recognition-on-und-x1","task":"Face Recognition","dataset":"UND-X1","model":"DPM","rank_in_archive_order":2,"of":2,"metrics":{"Rank-1":"83.73"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}