{"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/exploiting-temporal-and-depth-information-for","title":"Exploiting temporal and depth information for multi-frame face anti-spoofing","arxiv_id":"1811.05118","date":"2018-11-13","proceeding":null,"authors":["Zezheng Wang","Chenxu Zhao","Yunxiao Qin","Qiusheng Zhou","Guo-Jun Qi","Jun Wan","Zhen Lei"],"abstract":"Face anti-spoofing is significant to the security of face recognition\nsystems. Previous works on depth supervised learning have proved the\neffectiveness for face anti-spoofing. Nevertheless, they only considered the\ndepth as an auxiliary supervision in the single frame. Different from these\nmethods, we develop a new method to estimate depth information from multiple\nRGB frames and propose a depth-supervised architecture which can efficiently\nencodes spatiotemporal information for presentation attack detection. It\nincludes two novel modules: optical flow guided feature block (OFFB) and\nconvolution gated recurrent units (ConvGRU) module, which are designed to\nextract short-term and long-term motion to discriminate living and spoofing\nfaces. Extensive experiments demonstrate that the proposed approach achieves\nstate-of-the-art results on four benchmark datasets, namely OULU-NPU, SiW,\nCASIA-MFSD, and Replay-Attack.","url_abs":"http://arxiv.org/abs/1811.05118v3","url_pdf":"http://arxiv.org/pdf/1811.05118v3.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":"exploiting-temporal-and-depth-information-for","repo_url":"https://github.com/laoshiwei/face-anti-spoofing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"face-anti-spoofing","task_name":"Face Anti-Spoofing"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.05118","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}