@misc{https://doi.org/10.48550/arxiv.2104.00650,<br/><span class="tab"></span>
  doi = {10.48550/ARXIV.2104.00650},<br/><span class="tab"></span>
  url = {https://arxiv.org/abs/2104.00650},<br/><span class="tab"></span>
  author = {Bain,<br/><span class="tab"></span> Max and Nagrani,<br/><span class="tab"></span> Arsha and Varol,<br/><span class="tab"></span> Gül and Zisserman,<br/><span class="tab"></span> Andrew},<br/><span class="tab"></span>
  keywords = {Computer Vision and Pattern Recognition (cs.CV),<br/><span class="tab"></span> FOS: Computer and information sciences,<br/><span class="tab"></span> FOS: Computer and information sciences},<br/><span class="tab"></span>
  title = {Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval},<br/><span class="tab"></span>
  publisher = {arXiv},<br/><span class="tab"></span>
  year = {2021},<br/><span class="tab"></span>
  copyright = {Creative Commons Attribution 4.0 International}
}