Dataset Groups Activity Stream CoBIT Dataset The dataset used for training and evaluation of the CoBIT model, which consists of image-text pairs from large-scale noisy web-crawled data and image annotation data. BibTex: @dataset{Haoxuan_You_and_Mandy_Guo_and_Zhecan_Wang_and_Kai-Wei_Chang_and_Jason_Baldridge_and_Jiahui_Yu_2024, abstract = {The dataset used for training and evaluation of the CoBIT model, which consists of image-text pairs from large-scale noisy web-crawled data and image annotation data.}, author = {Haoxuan You and Mandy Guo and Zhecan Wang and Kai-Wei Chang and Jason Baldridge and Jiahui Yu}, doi = {10.57702/d1w8azbg}, institution = {No Organization}, keyword = {'image-text pairs', 'large-scale dataset', 'vision-language'}, month = {dec}, publisher = {TIB}, title = {CoBIT Dataset}, url = {https://service.tib.eu/ldmservice/dataset/cobit-dataset}, year = {2024} }