Hu Xu

9

Papers

230

Total Citations

Papers (9)

Demystifying CLIP Data

MoDE: CLIP Data Experts via Clustering

CiT: Curation in Training for Effective Vision-Language Data

Diffusion Models as Masked Autoencoders

DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment

Robust Small Object Detection on the Water Surface Through Fusion of Camera and Millimeter Wave Radar

Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning

Masked Autoencoders that Listen

MAViL: Masked Audio-Video Learners