Computer vision
Teaching machines to interpret and reason about the visual world, from object recognition to medical imaging.
Video
Learning From and Dealing With Real, Rare World Data In Computer Vision
Computer Vision has achieved tremendous progress in recent years. Primarily because of the availability of massive datasets (e.g., ImageNet or the Yahoo YFCC100m) as well as novel algorithms (e.g., deep learning or large-scale SfM pipelines).…
Microsoft Research Blog
Class of 2018-19 PhD fellows to push frontiers of AI
Class of 2018-19 PhD fellows to push frontiers of AI By Sandy Blyth A graduate student working on technology that leverages human brain signals to accelerate robot learning and another student who is developing models…
Video
Dreaming Contextual Memory
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels. Many applications have been found in diverse areas ranging from language modeling to document…
Video
Deep Learning Approach for Extreme Multi-label Text Classification
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels. Many applications have been found in diverse areas ranging from language modeling to document…
Video
EZLearn: Exploiting Organic Supervision in Large-Scale Data Annotation
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels. Many applications have been found in diverse areas ranging from language modeling to document…
Video
Precision-Recall versus Accuracy and the Role of Large Data Sets
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels. Many applications have been found in diverse areas ranging from language modeling to document…
Video
A Reduction Principle for Generalizing Bona Fide Risk Bounds in Multi-class Setting
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels. Many applications have been found in diverse areas ranging from language modeling to document…
