Weitong Cai

Weitong Cai is a Visiting Professor at Queen Mary University of London's School of Electronic Engineering and Computer Science. He specializes in teaching advanced topics like Deep Learning and Computer Vision at the postgraduate level. His research focuses on computer vision applications, including video moment retrieval, image segmentation, and cross-modal learning. He has contributed to advancements in temporal feature refinement, semantic localization, and robust image super-resolution techniques.

Research Interests: His work bridges theoretical machine learning methodologies with practical applications in multimedia systems and dynamic scene analysis. Key areas include:

• Video moment retrieval using hybrid learning frameworks
• Camouflaged object segmentation via prompt-agnostic methods
• Multi-domain adaptation in video analysis
• Efficient screen content coding

Publication Trends: Recent work emphasizes mitigating modality imbalance in cross-modal tasks (2025), improving temporal localization accuracy (2024), and robust image processing under complex degradations (2020-2019). His research spans both foundational algorithms and real-world applications like RGB-D SLAM in dynamic environments.

Advising & Grants: No specific grants or advisee名单 listed. Active in collaborative research with industry through the School's qTech Programme.

Labs/Teams: Participates in the School's Computer Vision and Machine Learning research groups, contributing to the qTech innovation ecosystem.