WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning.

@inproceedings{srinivasan-2021-wit, author = {Krishna Srinivasan and Karthik Raman and Jiecao Chen and Michael Bendersky and Marc Najork}, editor = {Fernando Diaz and Chirag Shah and Torsten Suel and Pablo Castells and Rosie Jones and Tetsuya Sakai}, title = {{WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning}}, booktitle = {{SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, Canada, July 11-15, 2021}}, pages = {2443--2449}, publisher = {ACM}, year = {2021}, url = {https://doi.org/10.1145/3404835.3463257}, doi = {https://doi.org/10.1145/3404835.3463257} }