@inproceedings{NEURIPS2022_3ea31343, author = {Tang, Zineng and Cho, Jaemin and Nie, Yixin and Bansal, Mohit}, booktitle = {Advances in Neural Information Processing Systems}, editor = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh}, pages = {9617--9632}, publisher = {Curran Associates, Inc.}, title = {TVLT: Textless Vision-Language Transformer}, url = {https://proceedings.neurips.cc/paper_files/paper/2022/file/3ea3134345f2e6228a29f35b86bce24d-Paper-Conference.pdf}, volume = {35}, year = {2022} }