@article{patchlevelsoundingobjecttrackingfor, title = {Patch-level Sounding Object Tracking for Audio-Visual Question Answering}, author = {Zhangbin Li and Jinxing Zhou and Jing Zhang and Shengeng Tang and Kun Li and Dan Guo}, year = {2024}, eprint = {2412.10749}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.10749v1}, }