Broadly, we aim to solve novel intriguing problems at the intersection of computer vision and natural language processing, by developing scalable machine learning and optimization techniques.

Our research agenda can be better understood by three groups of projects on which we are actively working:
(1) Research on recognition tasks of computer vision and their integration with natural language processing.
(2) Research on machine learning for computer vision and natural language processing.
(3) Understanding and generation of online multi-modal data such as photos, videos and natural text.

Please visit our lab's homepage for more detail.