My research interests are in machine learning and computer vision. Currently I particularly focus on zero-shot learning (ZSL) and vision-language related problems (specifically visual question answering).

My short-term goal on ZSL is to develop algorithms that can benefit from different kinds of semantic information (i.e., beyond attributes) and to develop preliminary theoretical foundation. For visual question answering, rather than designing novel algorithms to achieve the state-of-the-art results, Iím more interested in investigating the quality of the datasets and the prediction/evaluation criteria widely-adopted in recent literature.