VCR: Pixel-Level Complex Reasoning by Restoring Occluded Text
Jan 1, 2025·,,,,,,,,·
0 min read
Suyuchen Wang*
Tianyu Zhang*
Lu Li
Ge Zhang
Perouz Taslakian
Sai Rajeswar
Jie Fu
Bang Liu
Yoshua Bengio

Type
Publication
The Thirteenth International Conference on Learning Representations (ICLR 2025)