Yuan-Hong Liao (Andrew) Ph.D. Student at the University of Toronto

Research projects


Synthesizing Environment-Aware Activities via Activity Sketches
Yuan-Hong Liao*, Xavier Puig*, Marko Boben, Antonio Torralba, Sanja Fidler
CVPR 2019 in Long Beach, California USA
[paper] [code] [page]

Multi-view to Novel view: Synthesizing novel views with Self-Learned Confidence
Shao-Hua Sun , Minyoung Huh , Yuan-Hong Liao , Ning Zhang , Joseph J. Lim
ECCV 2018 in Munich, Germany
[paper] [code] [page]

Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner
Tseng-Hung Chen , Yuan-Hong Liao , Ching-Yao Chuang , Wan-Ting Hsu ,Jianlong Fu , Min Sun
ICCV 2017 in Venice, Italy
[arXiv] [code] [page]

Tactics for Adversarial Attack on Deep Reinforcement Learning Agents
Yen-Chen Lin , Zhang-Wei Hong , Yuan-Hong Liao , Meng-Li Shih , Ming-Yu Liu , Min Sun
IJCAI 2017, ICLR 2017 workshop in Melbourne, Australia
[arXiv] [page]

Leveraging Video Descriptions to Learn Video Question Answering
Kuo-Hao Zeng , Tseng-Hung Chen , Ching-Yao Chuang , Yuan-Hong Liao ,Juan Carlos Niebles , Min Sun
AAAI 2017 in San Francisco, California USA
[arXiv] [page]


Selected side projects


Implementation of Generative Adversarial Imitation Learning
One of the main contributor of @openai/baselines, one of the most widely-used RL repository. The original code is released at here.

Everyone has its own time zone.