@article{efficientmultiscalemultimodalbottleneck, title = {Efficient Multiscale Multimodal Bottleneck Transformer for Audio-Video Classification}, author = {Wentao Zhu}, year = {2024}, eprint = {2401.04023}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.04023v1}, }