@article{everythingatoncemultimodalfusion, title = {Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval}, author = {Nina Shvetsova and Brian Chen and Andrew Rouditchenko and Samuel Thomas and Brian Kingsbury and Rogerio Feris and David Harwath and James Glass and Hilde Kuehne}, year = {2021}, eprint = {2112.04446}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2112.04446v2}, }