@article{iseewhatyouhearavisioninspiredmethod, title = {I see what you hear: a vision-inspired method to localize words}, author = {Mohammad Samragh and Arnav Kundu and Ting-yao Hu and Minsik Cho and Aman Chadha and Ashish Shrivastava and Oncel Tuzel and Devang Naik}, year = {2022}, eprint = {2210.13567}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2210.13567v1}, }