Computer Vision
Enabling computers and devices to understand what they see.
Video
Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing
Presented by the Microsoft Health Futures team at CVPR 2023. [Publication] Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing
Tool
Temporal Vision-Language Processing (BioViL-T)
BioViL-T is a Vision-Language model trained on sequences of biomedical image and text data at a scale. It does not require manual annotations and can leverage historical raw clinical image acquisitions and clinical notes. The…
Project
Living Display
The purpose of this research is to provide an immersive, visually natural videoconferencing experience that is much closer to an in-person, face-to-face meeting than existing conferencing products.
Tool
Biomedical Visual-Language Processing (BioViL)
BioViL is a machine learning model trained on biomedical vision and language datasets at scale. It does not require manual annotations and can leverage historical raw clinical image acquisitions and clinical notes.