IEEE Transactions on Geoscience and Remote Sensing · 2020
Cited
24
Resume (English only)
Academic Achievements
PAMI Mark Everingham Prize Career Award (Oct 2025)
CVPR 2025: Self-Supervised Spatial Correspondence Across Modalities
ECCV 2024: Self-Supervised Any-Point Tracking by Contrastive Random Walks
CVPR 2023: EXIF as Language: Learning Cross-Modal Associations Between Images and Camera Metadata
CoRL 2020: Sim-to-Real Transfer for Vision-and-Language Navigation
ECCV 2020 Spotlight: Improving Vision-and-Language Navigation with Image-Text Pairs from the Web
NeurIPS 2019: Chasing Ghosts: Instruction Following as Bayesian State Tracking
Background
Research interests include computer vision and multimodal learning across vision, language, and audio. Particularly interested in self-supervised methods for learning visual correspondences, as well as image and video generation.
Miscellany
Organized or co-organized multiple Visual Question Answering and Dialog Workshops and Challenges; Participated in Google Summer of Code projects; Presented Memento project at code.fun.do SHOWCASE 2017.