Computer Vision
Enabling computers and devices to understand what they see.
Microsoft Research Blog
Microsoft and NVIDIA introduce parameter-efficient multimodal transformers for video representation learning
Understanding video is one of the most challenging problems in AI, and an important underlying requirement is learning multimodal representations that capture information about objects, actions, sounds, and their long-range statistical dependencies from audio-visual signals. Recently,…
Tool
Vision Longformer for Object Detection
This project provides the source code for the object detection part of vision longformer paper.
Microsoft Research Blog
Hands-on research and prototyping for haptics
While many of us think of human-computer interaction as a job for the eyes, ears and mind, we don’t think as often about the importance and complexity of our tactile interactions with computers. Haptics –…
Publication