EVENT

Talk on "Advancing Visual Understanding and Generation: Recent Research from NTHU Computer Vision Lab" by Shang-Hong Lai (National Tsing Hua University, Taiwan)

We are pleased to inform you about the upcoming seminar by Shang-Hong Lai (National Tsing Hua University, Taiwan) titled:"Advancing Visual Understanding and Generation: Recent Research from NTHU Computer Vision Lab" Everyone interested is cordially invited to attend!

Title:

Advancing Visual Understanding and Generation: Recent Research from NTHU Computer Vision Lab

Abstract:

In this talk, I will present some recent research works from the Computer Vision Laboratory at National Tsing Hua University (NTHU). The NTHU CV Lab focuses on several key areas, including video understanding, face-related analysis, anomaly detection, and medical imaging.

I will begin with two of our latest advances in video understanding, HERMES and VADER. HERMES introduces two versatile modules that can be seamlessly integrated into existing video-language models or deployed as a standalone framework for long-form video comprehension, achieving state-of-the-art performance across multiple benchmarks. VADER, on the other hand, is an LLM-driven framework for video anomaly reasoning, which combines keyframe-level object-relation modeling with visual contextual cues to enhance anomaly interpretation.

Next, I will discuss one of our recent works in anomaly detection, LFQUIAD.
LFQUIAD integrates a quantization-driven autoencoder with a modular Anomaly Generation Module to improve representation learning. Finally, I will briefly present two medical imaging projects leveraging diffusion models: one for generating paired 3D CT image-mask datasets, and the other for synthesizing contrast-enhanced 3D CT volumes from non-contrast scans.

Through these examples, I will highlight our lab's ongoing efforts toward building generalizable, interpretable, and efficient computer vision systems bridging visual understanding and generative modeling.

Speaker's bio:

Shang-Hong Lai is a Professor in the Department of Computer Science at National Tsing Hua University (NTHU), Taiwan, where he also serves as the Associate Dean of the College of Electrical Engineering and Computer Science (EECS). From 2018 to 2022, Dr. Lai was on leave at the Microsoft AI R&D Center in Taiwan, where he worked as a Principal Research Manager, leading a science team focused on face-related AI research.
Dr. Lai's research interests span computer vision, image processing, and machine learning. He has authored over 300 publications in leading international journals and conferences in these fields and holds approximately 30 patents related to computer vision and medical imaging technologies. He has served as Area, Theme, or Program Chair for major international conferences such as CVPR, ICCV, ECCV, NeurIPS, ICML, IJCAI, ACCV, and ICPR, and as an Associate Editor for International Journal of Computer Vision (IJCV), IEEE Transactions on Image Processing (TIP), and Pattern Recognition.

Shang-Hong Lai (National Tsing Hua University, Taiwan)

Time/Date:

16:00-17:00 November 12 (Wednesday), 2025

Place:

Room 1509, NII and online

Contact:

If you would like to join, please contact by email.
Email :sugimoto[at]nii.ac.jp