Keynote Talk<\/strong>:
Video Human Action Understanding<\/h2>\n<\/div>![\"\"](\"https:\/\/vap.aau.dk\/rws\/wp-content\/uploads\/sites\/10\/2026\/09\/fra.png\")
<\/figure><\/div>\n\n\n\nFran\u00e7ois Br\u00e9mond <\/strong>is a Research Director at the Inria Research Center of the University of Nice C\u00f4te d\u2019Azur, where he created the STARS team in 2012. He has pioneered the combination of Artificial Intelligence, Machine Learning, and Computer Vision for Video Understanding since 1993, both at Sophia-Antipolis and at USC (University of Southern California), LA. In 1997, he obtained his PhD degree in video understanding and pursued this work at USC on the interpretation of videos taken from UAVs (Unmanned Aerial Vehicles). In 2000, recruited as a researcher at Inria, he modeled human behavior for Scene Understanding: perception, multi-sensor fusion, spatio-temporal reasoning, and activity recognition. He is a co-founder of Keeneo, Ekinnox, and Neosensys, three companies in intelligent video monitoring and business intelligence. He also co-founded the CoBTek team at Nice University in January 2012 with Prof. P. Robert from Nice Hospital on the study of behavioral disorders for older adults suffering from dementia. He is the author or co-author of more than 300 scientific papers published in international journals or conferences on video understanding. He has (co)- supervised 30 PhD theses. More information is available at: http:\/\/www-sop.inria.fr\/members\/Francois.Bremond\/<\/a><\/p>\n\n\n\n\nKeynote Talk:
How Can We Detect Subtle, Hidden Activities and Organized Crime 24\/7? <\/h2>\n<\/div>![\"\"](\"https:\/\/vap.aau.dk\/rws\/wp-content\/uploads\/sites\/10\/2026\/09\/egor.png\")
<\/figure><\/div>\n\n\n\nEgor Bondarev<\/strong> is a professor in Computer Vision, heading the AIMS research group at Eindhoven University of Technology (TU\/e), The Netherlands. His research focuses on two core challenges: a) detection of subtle anomalies in human behavior or industrial assets without relying on labeled anomaly datasets; and b) the fusion of multi-modal sensor data, such as 2D, 3D, thermal, acoustic into accurate 3D spatio-temporal scene analysis to enable real-time situational awareness. Complementing this work, he contributes to sparsification and deployment of AI models on edge devices, as well as explainable AI techniques that support privacy preservation. Bondarev serves as a technical leader and principal investigator in several large European projects, including SMART Mobility, SINTRA, ELEVATION, and ADVISOR, and has led valorization and exploitation of resulting AI models with industrial and research partners, such as STMicroelectronics, ViNotion, and ProDrive.<\/p>\n\n\n\n\nKeynote Talk: Agentic AI for the Edge<\/h2>\n<\/div>![\"\"](\"https:\/\/vap.aau.dk\/rws\/wp-content\/uploads\/sites\/10\/2026\/09\/canva-buildable-instagram-ui-filled-person-icon-MAEuj_OEQ9I.webp\")
<\/figure><\/div>\n\n\n\n
Shuai\u00a0Zhang<\/strong>\u00a0is a Senior Staff Engineer and Manager in the Multimedia group at Qualcomm, specializing in Edge AI technologies, including segmentation, foundation models, and multi-modal AI. He earned his Ph.D. in Mathematics from the University of California, Irvine, in 2017. At Qualcomm,\u00a0Shuai\u00a0led the development of the Segmentation-based Cognitive ISP, which received the 2023 Edge AI and Vision Product of the Year Award. In 2024, his team\u2019s “Limitless Segmentation” solution was showcased as a flagship feature at the Qualcomm Summit, generating over 47K Google search results by October 29, 2024. Currently, he is leading the team working on the agentic visual intelligence and analysis system crossing edge and server. Shuai\u2019s research has resulted in 18 granted patents and 24 publications in top-tier journals and conferences, with over 1,500 citations. He is a Senior Member of IEEE and serves as the primary organizer of the IEEE Low Power Computer Vision Challenge and the Efficient Deep Learning for Computer Vision Workshop in 2025 and 2026.<\/p>\n\n\n\n
\n\n\n\n![\"\"](\"https:\/\/vap.aau.dk\/rws\/wp-content\/uploads\/sites\/10\/2025\/10\/contributors-1-1024x199.jpg\")
<\/figure>\n\n\n\n<\/div>\n\n\n\n<\/p>\n","protected":false},"excerpt":{"rendered":"
Keynote Talk:Video Human Action Understanding Fran\u00e7ois Br\u00e9mond is a Research Director at the Inria Research Center of the University of Nice C\u00f4te d\u2019Azur, where he created the STARS team in 2012. He has pioneered the combination of Artificial Intelligence, Machine Learning, and Computer Vision for Video Understanding since 1993, both at Sophia-Antipolis and at USC […]<\/p>\n","protected":false},"author":8,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-17","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/pages\/17","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/comments?post=17"}],"version-history":[{"count":8,"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/pages\/17\/revisions"}],"predecessor-version":[{"id":262,"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/pages\/17\/revisions\/262"}],"wp:attachment":[{"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/media?parent=17"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
<\/figure><\/div>\n\n\n\nFran\u00e7ois Br\u00e9mond <\/strong>is a Research Director at the Inria Research Center of the University of Nice C\u00f4te d\u2019Azur, where he created the STARS team in 2012. He has pioneered the combination of Artificial Intelligence, Machine Learning, and Computer Vision for Video Understanding since 1993, both at Sophia-Antipolis and at USC (University of Southern California), LA. In 1997, he obtained his PhD degree in video understanding and pursued this work at USC on the interpretation of videos taken from UAVs (Unmanned Aerial Vehicles). In 2000, recruited as a researcher at Inria, he modeled human behavior for Scene Understanding: perception, multi-sensor fusion, spatio-temporal reasoning, and activity recognition. He is a co-founder of Keeneo, Ekinnox, and Neosensys, three companies in intelligent video monitoring and business intelligence. He also co-founded the CoBTek team at Nice University in January 2012 with Prof. P. Robert from Nice Hospital on the study of behavioral disorders for older adults suffering from dementia. He is the author or co-author of more than 300 scientific papers published in international journals or conferences on video understanding. He has (co)- supervised 30 PhD theses. More information is available at: http:\/\/www-sop.inria.fr\/members\/Francois.Bremond\/<\/a><\/p>\n\n\n\n Egor Bondarev<\/strong> is a professor in Computer Vision, heading the AIMS research group at Eindhoven University of Technology (TU\/e), The Netherlands. His research focuses on two core challenges: a) detection of subtle anomalies in human behavior or industrial assets without relying on labeled anomaly datasets; and b) the fusion of multi-modal sensor data, such as 2D, 3D, thermal, acoustic into accurate 3D spatio-temporal scene analysis to enable real-time situational awareness. Complementing this work, he contributes to sparsification and deployment of AI models on edge devices, as well as explainable AI techniques that support privacy preservation. Bondarev serves as a technical leader and principal investigator in several large European projects, including SMART Mobility, SINTRA, ELEVATION, and ADVISOR, and has led valorization and exploitation of resulting AI models with industrial and research partners, such as STMicroelectronics, ViNotion, and ProDrive.<\/p>\n\n\n\n <\/p>\n","protected":false},"excerpt":{"rendered":" Keynote Talk:Video Human Action Understanding Fran\u00e7ois Br\u00e9mond is a Research Director at the Inria Research Center of the University of Nice C\u00f4te d\u2019Azur, where he created the STARS team in 2012. He has pioneered the combination of Artificial Intelligence, Machine Learning, and Computer Vision for Video Understanding since 1993, both at Sophia-Antipolis and at USC […]<\/p>\n","protected":false},"author":8,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-17","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/pages\/17","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/comments?post=17"}],"version-history":[{"count":8,"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/pages\/17\/revisions"}],"predecessor-version":[{"id":262,"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/pages\/17\/revisions\/262"}],"wp:attachment":[{"href":"https:\/\/vap.aau.dk\/rws\/wp-json\/wp\/v2\/media?parent=17"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}Keynote Talk:
How Can We Detect Subtle, Hidden Activities and Organized Crime 24\/7? <\/h2>\n<\/div><\/figure><\/div>\n\n\n\nKeynote Talk: Agentic AI for the Edge<\/h2>\n<\/div>
<\/figure><\/div>\n\n\n\n
Shuai\u00a0Zhang<\/strong>\u00a0is a Senior Staff Engineer and Manager in the Multimedia group at Qualcomm, specializing in Edge AI technologies, including segmentation, foundation models, and multi-modal AI. He earned his Ph.D. in Mathematics from the University of California, Irvine, in 2017. At Qualcomm,\u00a0Shuai\u00a0led the development of the Segmentation-based Cognitive ISP, which received the 2023 Edge AI and Vision Product of the Year Award. In 2024, his team\u2019s “Limitless Segmentation” solution was showcased as a flagship feature at the Qualcomm Summit, generating over 47K Google search results by October 29, 2024. Currently, he is leading the team working on the agentic visual intelligence and analysis system crossing edge and server. Shuai\u2019s research has resulted in 18 granted patents and 24 publications in top-tier journals and conferences, with over 1,500 citations. He is a Senior Member of IEEE and serves as the primary organizer of the IEEE Low Power Computer Vision Challenge and the Efficient Deep Learning for Computer Vision Workshop in 2025 and 2026.<\/p>\n\n\n\n
\n\n\n\n<\/figure>\n\n\n\n