@article{clippoweredtasstargetawaresinglestream, title = {CLIP-Powered TASS: Target-Aware Single-Stream Network for Audio-Visual Question Answering}, author = {Yuanyuan Jiang and Jianqin Yin}, year = {2024}, eprint = {2405.07451}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.07451v1}, }