CVPR 2023 - EXIF as Language: Learning Cross-Modal

This episode is about the paper titled “EXIF as Language: Learning Cross-Modal” at CVPR 2023, by Chenhao Zheng, Ayush Shrivastava, and Andrew Owens from University of Michigan. In this paper, the authors propose a new approach to learning visual representations, which captures information about the camera that recorded a given photo.