@article {2106.12570, archivePrefix = {arXiv}, eprint = {2106.12570}, primaryClass = {cs.LG}, author = {Tom Joy and Yuge Shi and Philip H. S. Torr and Tom Rainforth and Sebastian M. Schmon and N. Siddharth}, title = {Learning Multimodal VAEs through Mutual Supervision}, year = {2021}, url = {http://arxiv.org/abs/2106.12570} }