Dataset Groups Activity Stream Crisscrossed Captions Crisscrossed Captions (CxC) dataset is a multimodal learning dataset used for training and evaluation of the MURAL model. BibTex: @dataset{Zarana_Parekh_and_Jason_Baldridge_and_Daniel_Cer_and_Austin_Waters_and_Yinfei_Yang_2024, abstract = {Crisscrossed Captions (CxC) dataset is a multimodal learning dataset used for training and evaluation of the MURAL model.}, author = {Zarana Parekh and Jason Baldridge and Daniel Cer and Austin Waters and Yinfei Yang}, doi = {10.57702/gyoivp1d}, institution = {No Organization}, keyword = {'Crisscrossed Captions', 'Image Captioning', 'Multimodal Learning'}, month = {dec}, publisher = {TIB}, title = {Crisscrossed Captions}, url = {https://service.tib.eu/ldmservice/dataset/crisscrossed-captions}, year = {2024} }
