Special Session 1: Multimodal AI for Video Understanding and Retrieval
Recent advances in artificial intelligence, particularly deep learning, vision-language models (VLMs), and generative AI, have significantly enhanced the capabilities of video understanding and retrieval. As large-scale video collections continue to grow, there is an increasing demand for intelligent technologies that can efficiently analyze, understand, and retrieve video content based on complex user queries. Despite substantial progress, challenges remain in multimodal representation learning, temporal understanding, semantic video retrieval, and interactive search. This Special Session aims to bring together researchers and practitioners to present recent advances in multimodal AI for video understanding and retrieval, including vision-language models, video question answering, human-in-the-loop retrieval, and applications to large-scale video collections.
Topics of interest for submission include, but are not limited to:
Special Session Chairs:
Assoc. Prof. Kazuya Ueki, Meisei University, Japan
He received his B.S. degree in Information Engineering in 1997 and his M.S. degree in Computer and Mathematical Sciences in 1999, both from Tohoku University, Sendai, Japan. In 1999, he joined NEC Soft, Ltd., Tokyo, Japan, where he was primarily engaged in research on face recognition. He received his Ph.D. degree from the Graduate School of Science and Engineering, Waseda University, Tokyo, Japan, in 2007. From 2013 to 2017, he served as an Assistant Professor at Waseda University. He is currently an Associate Professor in the School of Information Science at Meisei University, Japan. His research interests include information retrieval, video anomaly detection, pattern recognition, and machine learning. He has actively participated in TRECVID, a video retrieval evaluation benchmark organized by the National Institute of Standards and Technology (NIST), contributing to advances in video retrieval technology. His systems achieved the top performance in the TRECVID Ad-hoc Video Search (AVS) task in 2016, 2017, 2022, and 2025.
The manuscript should be submitted via the submission link (via the Electronic Submission System), or to icmlt_conf@163.com before the submission deadline.
