PolyViT: Co-training Vision Transformers on Images, Videos and Audio
Published in Arxiv, 2021
https://arxiv.org/abs/2111.12993
Valerii Likhosherstov, Anurag Arnab, Krzysztof Choromanski, Mario Lucic, Yi Tay, Adrian Weller and Mostafa Dehghani.
Valerii Likhosherstov
PhD student @ Cambridge Machine Learning Group. Graduated from UrFU SESC (high school), UrFU (B.S.), Yandex Data School, Skoltech & HSE (M.S.).
- Cambridge, The United Kingdom
- Github
- Google Scholar