Dataset Groups Activity Stream CC3M-595K The dataset used for training the Chat-UniVi model. BibTex: @dataset{Peng_Jin_and_Ryuichi_Takanobu_and_Wancai_Zhang_and_Xiaochun_Cao_and_Li_Yuan_2024, abstract = {The dataset used for training the Chat-UniVi model.}, author = {Peng Jin and Ryuichi Takanobu and Wancai Zhang and Xiaochun Cao and Li Yuan}, doi = {10.57702/u48zz4xz}, institution = {No Organization}, keyword = {'image understanding', 'multimodal conversation', 'video understanding'}, month = {dec}, publisher = {TIB}, title = {CC3M-595K}, url = {https://service.tib.eu/ldmservice/dataset/cc3m-595k}, year = {2024} }
