Research area

Computer Vision & Multimodal AI

Advancing visual understanding, vision-language models, object detection, and multimodal AI for real-world applications.

All research areas View publications

Overview

Work in this area covers how machines represent and reason about visual information, and how visual representations combine with other modalities such as text. Malaya AIR members publish on generative and diffusion models, deep hashing and retrieval, object and scene text detection, video understanding and industrial inspection. Several members work on both the vision and the language side of multimodal systems, which is why this area overlaps closely with the centre's natural language processing research and with its medical imaging work.