HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts Paper • 2404.17507 • Published Apr 26, 2024
Leveraging Temporal Contextualization for Video Action Recognition Paper • 2404.09490 • Published Apr 15, 2024
Learning with Unmasked Tokens Drives Stronger Vision Learners Paper • 2310.13593 • Published Oct 20, 2023