报告题目：

Interpretable Multimodal Depression Detection

报告时间：2026年4月14日下午14:00-16:00

报告地点：大连理工大学开发区校区信息楼三楼计算机广场报告厅

报告人：Dr. Varun Ojha, Newcastle University

报告内容（摘要）：

There are many explorations of how to bridge the gap between AI and clinical depression detection, from multimodal feature fusion and transfer learning to sentiment-aware representation and LLM reasoning. In this talk, I will first discuss our recent work on an Intra- and Inter-Emotion Transformer which captures stable depressive patterns across emotional states. Then, I will draw comparisons and insights between our work and existing methods in terms of efficient knowledge transfer, prompt-based enhancement, and explainable diagnostics.

报告人简介：

Jiaqing Liu received the B.E. degree in 2016 from Northeastern University, China, and the M.E. and the D.E. degree in 2018 and 2021, both from Ritsumeikan University, Shiga, Japan. From 2020 to 2021, he was a JSPS Research Fellow for Young Scientists. From October 2021 to March 2022, he served as a Specially Appointed Assistant Professor with the Department of Intelligent Media, ISIR, Osaka University, Osaka, Japan. He is currently an Assistant Professor in the College of Information Science and Engineering, Ritsumeikan University, Osaka, Japan. His research interests include computer vision, medical engineering, deep learning and multimodal interaction.