@InProceedings{Lavish_CVPR2023, author = {Yan-Bo Lin and Yi-Lin Sung and Jie Lei and Mohit Bansal and Gedas Bertasius}, title = {Vision Transformers are Parameter-Efficient Audio-Visual Learners}, booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023} }