• Learning and Vision Lab: Asst. Prof Xinchao Wang

The Computer Vision and Machine Learning group has focused on the most original research and technologies at the edges for computer vision, machine learning and their applications in real life. The group undertakes research projects from both industry and national research programs, that include fundamental machine learning and deep learning algorithms, cutting-edge face/human and image/video analytics technologies, and intelligent search and recommendation systems. The group delivered top performing systems in international benchmarking, such as ILSVRC2017 for image localization and MS-Celeb-1M for large-scale face recognition.

• Show Lab: Asst. Prof Mike Shou

Show lab aims to build AI Assistant on various platforms, including social media, metaverse/AR glass, robot, with the ability of understanding and creating video, audio, language collectively. This involves techniques like: Video Understanding e.g. video detection, segmentation in space and time, multi-modal e.g. video+language, video+audio, AI-Human interaction, generation and Digitization e.g. photorealistic avatar, video diffusion model.

• Vision and AI Lab: Assoc. Prof Robby Tan

Vision AI group focuses on research areas are in machine learning and AI, with a strong focus on computer vision, deep learning and foundation models. In computer vision, the group addresses the challenges in adverse outdoor conditions, human-centric analysis, and image forensics, particularly in detecting and analyzing fake images and videos. In foundation models, the work is geared up to multimodal input and agentic AI, with emphasis on agent reasoning and collaborations. The group aims to uncover the foundational principles behind knowledge acquisition and intelligence, integrating theoretical exploration with practical applications, in the domain of computer vision and beyond.

• Computational Brain Imaging Group: Assoc. Prof Thomas Yeo

The Computational Brain Imaging Group develops machine learning algorithms to generate scientific discoveries from population-level datasets with brain MRI, behavioral, genetic and other physiological measures. We are particularly interested in mapping brain networks in individuals and using brain network features to predict individual-level behavioral traits, mental disorder symptoms and disease progression. Insights from population-level studies are in turn used to develop personalized treatments for mental disorders.