{"id":1626,"date":"2026-01-07T12:00:00","date_gmt":"2026-01-07T04:00:00","guid":{"rendered":"https:\/\/cchsu.info\/wordpress\/2026\/01\/07\/news-umcl-published-in-ijcv\/"},"modified":"2026-01-07T12:00:00","modified_gmt":"2026-01-07T04:00:00","slug":"news-umcl-published-in-ijcv","status":"publish","type":"post","link":"https:\/\/cchsu.info\/wordpress\/2026\/01\/07\/news-umcl-published-in-ijcv\/","title":{"rendered":"[News] UMCL has been published in IJCV!"},"content":{"rendered":"<div class=\"news-paper-block\">\n<p><strong>Research Direction:<\/strong> Media Security \/ Trustworthy Media Forensics<\/p>\n<p><strong>Authors:<\/strong> C.-Y. Lai, C.-Y. Jian, P.-C. Chuang, C.-M. Lee, C.-C. Hsu, C.-T. Hsu, and C.-W. Lin<\/p>\n<p>Our paper <strong>UMCL: Unimodal-Generated Multimodal Contrastive Learning for Cross-compression-rate Deepfake Detection<\/strong> has been published in the <strong>International Journal of Computer Vision (IJCV)<\/strong>.<\/p>\n<p>UMCL studies a practical but difficult DeepFake detection setting: models often degrade when the compression level of the test video differs from that of the training data. To address this cross-compression-rate challenge, the paper derives multiple complementary cues from a single visual input, including rPPG signals, facial landmark dynamics, and semantic embeddings, and aligns them through contrastive learning for more robust detection.<\/p>\n<p>This work reflects our lab\u2019s ongoing efforts in <strong>trustworthy media analysis<\/strong>, <strong>robust vision under real-world degradations<\/strong>, and <strong>security-oriented visual intelligence<\/strong> that remains reliable beyond curated benchmark conditions.<\/p>\n<ul>\n<li><strong>Venue:<\/strong> International Journal of Computer Vision (IJCV)<\/li>\n<li><strong>Published online:<\/strong> 07 January 2026<\/li>\n<li><strong>Focus:<\/strong> Cross-compression-rate DeepFake detection and robust media forensics<\/li>\n<li><strong>Links:<\/strong> <a href=\"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02606-0\" target=\"_blank\" rel=\"noopener noreferrer\">Springer<\/a> | <a href=\"https:\/\/doi.org\/10.1007\/s11263-025-02606-0\" target=\"_blank\" rel=\"noopener noreferrer\">DOI<\/a><\/li>\n<\/ul>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Research Direction: Media Security \/ Trustworthy Media  [&hellip;]<\/p>\n","protected":false},"author":0,"featured_media":0,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[],"class_list":["post-1626","post","type-post","status-publish","format-standard","hentry","category-news"],"_links":{"self":[{"href":"https:\/\/cchsu.info\/wordpress\/wp-json\/wp\/v2\/posts\/1626","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cchsu.info\/wordpress\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cchsu.info\/wordpress\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/cchsu.info\/wordpress\/wp-json\/wp\/v2\/comments?post=1626"}],"version-history":[{"count":0,"href":"https:\/\/cchsu.info\/wordpress\/wp-json\/wp\/v2\/posts\/1626\/revisions"}],"wp:attachment":[{"href":"https:\/\/cchsu.info\/wordpress\/wp-json\/wp\/v2\/media?parent=1626"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cchsu.info\/wordpress\/wp-json\/wp\/v2\/categories?post=1626"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cchsu.info\/wordpress\/wp-json\/wp\/v2\/tags?post=1626"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}