Xue Hong-wei

CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment

Xue Hong-wei, Yuchong Sun, Bei Liu et al. · arXiv (Cornell University) · 2022 · 53 citations · Full text

Engineering, Machine Learning, Multimodal Learning +16

Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning

Yuchong Sun, Xue Hong-wei, Ruihua Song et al. · arXiv (Cornell University) · 2022 · 33 citations · Full text

Engineering, Machine Learning, Multimodal Learning +17

Stare at What You See: Masked Image Modeling without Reconstruction

Xue Hong-wei, Peng Gao, Hongyang Li et al. · 2023 · 22 citations

Engineering, Machine Learning, Masked Regions +19