@article{audiovisualtransformerarchitecturesfor, title = {Audiovisual Transformer Architectures for Large-Scale Classification and Synchronization of Weakly Labeled Audio Events}, author = {Wim Boes and Hugo Van hamme}, year = {2019}, eprint = {1912.02615}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1912.02615v1}, }