Dataset Groups Activity Stream Laion-20M The dataset used for pre-training the MS-CLIP model, which consists of 20 million image-text pairs filtered from Laion-400M. BibTex: @dataset{Haoxuan_You_and_Luowei_Zhou_and_Bin_Xiao_and_Noel_Codella_and_Yu_Cheng_and_Ruochen_Xu_and_Shih-Fu_Chang_and_Lu_Yuan_2024, abstract = {The dataset used for pre-training the MS-CLIP model, which consists of 20 million image-text pairs filtered from Laion-400M.}, author = {Haoxuan You and Luowei Zhou and Bin Xiao and Noel Codella and Yu Cheng and Ruochen Xu and Shih-Fu Chang and Lu Yuan}, doi = {10.57702/070kx7rz}, institution = {No Organization}, keyword = {'MS-CLIP', 'image-text pairs', 'pre-training'}, month = {dec}, publisher = {TIB}, title = {Laion-20M}, url = {https://service.tib.eu/ldmservice/dataset/laion-20m}, year = {2024} }
