{"id":16,"date":"2018-01-12T11:49:01","date_gmt":"2018-01-12T02:49:01","guid":{"rendered":"https:\/\/kaumediaprocessing.wordpress.com\/?page_id=16"},"modified":"2026-07-08T02:14:07","modified_gmt":"2026-07-08T02:14:07","slug":"research","status":"publish","type":"page","link":"http:\/\/multimedia.kau.ac.kr\/?page_id=16","title":{"rendered":"<strong>Research<\/strong>"},"content":{"rendered":"<p><span style=\"color: #3d85c6; font-size: 21px;\"><strong> R1. Video forensics <\/strong> <\/span><br \/>\n<span style=\"color: #000000; font-size: 15px;\"> Video forensics is an investigation technique for detecting manipulated(forged) video, and is a key technology for solving various image\/video related legal problems.<\/span><\/p>\n<p><span style=\"color: #000000; font-size: 16px;\"><b><strong> 1.1 Generalization of Deep Faked Image\/Video Detection<\/strong><\/b><\/span><br \/>\n<img decoding=\"async\" class=\"alignnone wp-image-192\" src=\"http:\/\/multimedia.kau.ac.kr\/wp-content\/uploads\/2024\/08\/Deepfake.jpg?w=200\" alt=\"\" width=\"400\"><br \/>\n<span style=\"color: #000000; font-size: 13px;\">[Face2Parts: Exploring coarse-to-fine inter-regional facial dependencies for generalized deepfake detection, 2026]<\/span><\/p>\n<p><span style=\"color: #000000; font-size: 16px;\"><b><strong> 1.2 Counter Anti-forensic for Defending Adversarial Attacks<\/strong><\/b><\/span><\/p>\n<p><img decoding=\"async\" class=\"alignnone wp-image-579\" src=\"http:\/\/multimedia.kau.ac.kr\/wp-content\/uploads\/2024\/07\/CAF_system.png\" alt=\"\" width=\"780\"><br \/>\n<span style=\"color: #000000; font-size: 13px;\">[A robust open-set multi-instance learning for defending adversarial attacks in digital image, 2024.]<\/span><br \/>\n<span style=\"color: #000000; font-size: 13px;\">[Counter-act against GAN-based attacks: A collaborative learning approach for anti-forgery detection, 2024.] <span style=\"color: #000000\"><\/span><\/span><\/p>\n<p><span style=\"color: #000000; font-size: 16px;\"><b><strong> 1.3 Detection of Double Compression<\/strong><\/b><\/span><br \/>\n<img decoding=\"async\" class=\"alignnone wp-image-579\" src=\"http:\/\/multimedia.kau.ac.kr\/wp-content\/uploads\/2023\/07\/DetectionDC.jpg\" alt=\"\" width=\"600\"> <a>&nbsp;<\/a><br \/>\n<span style=\"color: #000000; font-size: 13px;\">[Deep learning-based counter anti-forensic of GAN-based attack in HEVC compressed domain using coding pattern analysis, 2023.] <span style=\"color: #000000\"><\/span><br \/>\n<span style=\"color: #000000; font-size: 13px;\">[Double compression detection in HEVC-coded video with the same coding parameters using picture partitioning information, 2022.]<\/span><\/span><\/p>\n<p><span style=\"color: #3d85c6; font-size: 21px;\"><strong> R2. Point Cloud Processing <\/strong> <\/span><\/p>\n<p><span style=\"color: #000000; font-size: 16px;\"><b><strong> 2.1 Point Cloud Rendering <\/strong><\/b><\/span><\/p>\n<p><img decoding=\"async\" class=\"alignnone wp-image-579\" src=\"http:\/\/multimedia.kau.ac.kr\/wp-content\/uploads\/2026\/04\/CRISP.png\" alt=\"\" width=\"700\"><br \/>\n<span style=\"color: #000000; font-size: 13px;\">[CRISP: Cylindrical rendering for in-stream point clouds, 2026.]<\/span><br \/>\n<span style=\"color: #000000; font-size: 13px;\">[Rendering compressed point clouds with a voxel-based method, 2025.]<\/span><br \/>\n<span style=\"color: #000000; font-size: 13px;\">[Point-based volumetric surface rendering via multi-projection, 2024.]<\/span><\/p>\n<p><span style=\"color: #000000; font-size: 16px;\"><b><strong> 2.2 Feature Extractions for Point Cloud Data <\/strong><\/b><\/span><br \/>\n<img decoding=\"async\" class=\"alignnone wp-image-579\" src=\"http:\/\/multimedia.kau.ac.kr\/wp-content\/uploads\/2024\/08\/PointCloudFeature.jpg\" alt=\"\" width=\"780\"> <a> <\/a><br \/>\n<span style=\"color: #000000; font-size: 13px;\">[A versatile point view descriptor of multi-view depth images for 3D shape classification, In preparation.] <span style=\"color: #000000; font-size: 12px;\"><\/span><\/span><\/p>\n<p><span style=\"color: #3d85c6; font-size: 21px;\"><strong> R3. 3D Image\/Video Processing <\/strong> <\/span><\/p>\n<p><span style=\"color: #000000; font-size: 16px;\"><b><strong> 3.1 Immersive Video Processing <\/strong><\/b><\/span><\/p>\n<p><img decoding=\"async\" class=\"alignnone wp-image-579\" src=\"http:\/\/multimedia.kau.ac.kr\/wp-content\/uploads\/2023\/07\/RL.jpg\" alt=\"\" width=\"600\"><br \/>\n<span style=\"color: #000000; font-size: 13px;\">[Inactive region filling method for efficient compression using reinforcement learning, 2023.]<\/span><\/p>\n<p><span style=\"color: #000000; font-size: 16px;\"><b><strong> 3.2 Depth Map Processing <\/strong><\/b><\/span><br \/>\n<img decoding=\"async\" class=\"alignnone wp-image-579\" src=\"http:\/\/multimedia.kau.ac.kr\/wp-content\/uploads\/2020\/10\/Network_displacement_vector_warping.png\" alt=\"\" width=\"450\"> <a> <\/a><br \/>\n<span style=\"color: #000000; font-size: 13px;\">[Deep convolutional grid warping network for joint depth map upsampling, 2020.] <span style=\"color: #000000\"><\/span><\/span><br \/>\n<span style=\"color: #000000; font-size: 13px;\">[Depth map upsampling with a confidence-based joint guided filter, 2019.] <span style=\"color: #000000\"><\/span><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>R1. Video forensics Video forensics is an investigation technique for detecting manipulated(forged) video, and is a key technology for solving various image\/video related legal problems. 1.1 Generalization of Deep Faked Image\/Video Detection [Face2Parts: Exploring coarse-to-fine inter-regional facial dependencies for generalized deepfake detection, 2026] 1.2 Counter Anti-forensic for Defending Adversarial Attacks [A robust open-set multi-instance learning &hellip; <a href=\"http:\/\/multimedia.kau.ac.kr\/?page_id=16\" class=\"more-link\">Continue reading <span class=\"screen-reader-text\"><strong>Research<\/strong><\/span> <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"parent":0,"menu_order":3,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-16","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"http:\/\/multimedia.kau.ac.kr\/index.php?rest_route=\/wp\/v2\/pages\/16","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/multimedia.kau.ac.kr\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"http:\/\/multimedia.kau.ac.kr\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"http:\/\/multimedia.kau.ac.kr\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"http:\/\/multimedia.kau.ac.kr\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=16"}],"version-history":[{"count":59,"href":"http:\/\/multimedia.kau.ac.kr\/index.php?rest_route=\/wp\/v2\/pages\/16\/revisions"}],"predecessor-version":[{"id":1247,"href":"http:\/\/multimedia.kau.ac.kr\/index.php?rest_route=\/wp\/v2\/pages\/16\/revisions\/1247"}],"wp:attachment":[{"href":"http:\/\/multimedia.kau.ac.kr\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=16"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}