About me

I am a second year Ph.D student in Computer Science at Australian National University. My supervision panel includes Ben Swift, Hanna Suominen and Hongdong Li.

I am interested in the intersection of language and vision, or in general, cross-modality learning problems that require models to fuse together inputs and outputs of different forms. My recent work is around video representation learning and text generation from video input.

Before coming back to research study, I worked in industry as a data scientist for a few years and I have been involved in a variety of interesting problems such as 3D fitting optimization and assortment/category optimization.

News

• [2021.12] Paper accepted to AAAI 2022.
• [2021.02] Paper accepted to CVPR 2021.
• [2020.11] Demonstration paper accepted to WSDM 2021.
• [2020.10] Paper accepted to NeurIPS 2020.
• [2020.2] Paper accepted to CVPR 2020.