Hongmei Zhang, Guilin University of Electronic Technology, China

Dr. Zhang Hongmei is currently a professor in Guilin University of Electronic Technology. She received her Ph.D. in Pattern Recognition and Intelligent Systems from East China University of Science and Technology in 2008. She broadened her academic perspective through visiting scholar positions at National Cheng Kung University in Taiwan in 2010, and subsequently at Heriot-Watt University in the UK from 2014 to 2015. Her research areas include information system security, machine learning and embedded system. She has successfully led many projects, including a Regional Program of NSFC, Guangxi Key Natural Science Foundation projects, and initiatives from various provincial key laboratories and engineering research centers. She has published over 70 academic papers in prestigious journals, with more than 30 of these being indexed by SCI and EI. Beyond her research and publications, she has made substantial contributions to the academic community; for instance, she acted as the organizer of the Chinacom 2013 International Conference. Furthermore, she held the position of associate editor for Wireless Communication and Mobile Computing, and currently serves as associate editor for IEEE Access. In addition, she has acted as Co-Chair for the IEEE INFOCOM 2011 Workshop on Cognitive & Cooperative Networks, a Session Chair or Invited Speaker for the IEEE International Conference on Communication Technology (ICCT) from 2020 to 2025, and a Session Chair for the 10th International Conference on Internet Computing for Science and Engineering (ICICSE 2021).

Speech Title: TBA
Abstract: TBA

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 mainly 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, Meisei University. His research interests include information retrieval, video anomaly detection, pattern recognition, and machine learning. He is involved in the video retrieval evaluation benchmark (TRECVID) sponsored by the National Institute of Standards and Technology (NIST), contributing to the development of video retrieval technology. His submitted systems achieved the highest performance in the TRECVID AVS task in 2016, 2017, 2022, and 2025.

Speech Title: From Keywords to Context: Five Years Toward Intent-Aware Video Search

Abstract: Video retrieval is often framed as a matching problem, yet real user intent is rarely captured by keywords alone. Over the past five years, our work has explored how to close this gap through three research questions. First, how can we enrich sparse or ambiguous queries to better reflect what users actually mean? Second, how can retrieval models adapt to new domains without manual annotation? Third, how can we verify that retrieved results truly satisfy the query's intent, rather than merely resembling it? We address these questions through query expansion with large language models and image generation, caption-driven domain adaptation, and VLM-based semantic verification via visual question answering. These techniques contributed to our team achieving the top rank in the TRECVID Ad-hoc Video Search (AVS) task in 2022 and 2025. The talk shares what worked, what didn't, and the challenges that remain in building video search systems that understand not just words, but user intent.