My research interests are mainly in computer vision and machine learning. My previous research projects include modeling visual objects regardless of depictive styles and image understanding using contextual cues. I am currently leading a small team at the Adelaide to research on the topic of Vision-and-Language.

I have been in the computer vision filed for nearly 6 years and I have a strong track record in this field. Currently, I am working on the vision to language problem and I am especially an expert in the image captioning and visual question answering (VQA). In 2015, my image captioning model and VQA model achieved the leading performance in the Microsoft COCO Image Captioning Challenges and VQA Challenges. I have published several papers in the top journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Signal Processing Magazine (SPM), Computer Vision and Image Understanding (CVIU). I also have published several papers on the top conference, such as International Joint Conference on Artificial Intelligence (IJCAI), AAAI, The Conference on Computer Vision and Pattern Recognition (CVPR) and the European Conference on Computer Vision (ECCV), and so on.