I am mainly interested in Computer Vision, Machine Learning, the intersection of Natural Language and Vision, and analysing the role of Semantics in Visual Understandings. More specifically, my research interests include:

Object and action recognition
Attribute based object representations and cross category generalization
Generating richer descriptions for images
Aspect issues in human activity and object recognition
Knowledge trasnfer, transfer learning and it's applications in computer vision
Scene understanding
Multitask learning and annotation prediction
Sign language recognition
Image segmentation