International Journal of Computer Assisted Radiology and Surgery · 2021
Cited
8
Resume (English only)
Academic Achievements
Winner of CVPR 2021 Best Student Paper HM; involved in multiple projects accepted by top conferences, such as MIST (CVPR 2023), Visual Clues (NeurIPS 2022), etc.
Research Experience
Currently a research scientist at Google Deepmind. Previously spent two years at Microsoft working on vision foundation models, including projects like FLorence and ClipBERT. Interned at FAIR, MSR, and Salesforce Research.
Education
Ph.D. degree: 2020 from the University of Michigan, supervised by Dr. Jason J. Corso; Bachelor's degree: 2015 from Nanjing University, worked on Multi-Agent RL.
Background
Research interests: Computer vision and its relations to natural language and deep learning, with a focus on learning visual representation from multimodal supervision. Problems of interest include multimodal learning (e.g., captioning, grounding, VQA), video understanding, unsupervised representation learning, generative models, and Transformers etc.