Lijie Fan

LaCLIP. [NeurIPS 2023] Text data, code and pre-trained models for paper "Improving CLIP Training with Language Rewrites"

tvnet. [CVPR 2018] End-to-End Learning of Motion Representation for Video Understanding

AdvCL. [NeurIPS 2021] “When does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?”