Tool
UDOP
UDOP adopts an encoder-decoder Transformer architecture based on T5 for document AI tasks like document image classification, document parsing and document visual question answering. You can use the model for document image classification, document parsing…
Publication
Neural Video Compression with Feature Modulation
Microsoft Research Blog
Research Focus: Week of February 19, 2024
In this issue: CaaSPER: vertical autoscaling algorithm dynamically maintains optimal CPU utilization; Improved scene landmark detection for camera localization runs faster, uses less storage; ESUS simplifies usability questionnaires for technical products and services.
Publication
Agent AI Towards a Holistic Intelligence
Publication