all AI news
Masked Autoencoders As Spatiotemporal Learners. (arXiv:2205.09113v1 [cs.CV])
May 19, 2022, 1:11 a.m. | Christoph Feichtenhofer, Haoqi Fan, Yanghao Li, Kaiming He
cs.LG updates on arXiv.org arxiv.org
This paper studies a conceptually simple extension of Masked Autoencoders
(MAE) to spatiotemporal representation learning from videos. We randomly mask
out spacetime patches in videos and learn an autoencoder to reconstruct them in
pixels. Interestingly, we show that our MAE method can learn strong
representations with almost no inductive bias on spacetime (only except for
patch and positional embeddings), and spacetime-agnostic random masking
performs the best. We observe that the optimal masking ratio is as high as 90%
(vs. 75% …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Praktikum im Bereich eMobility / Charging Solutions - Data Analysis
@ Bosch Group | Stuttgart, Germany
Business Data Analyst
@ PartnerRe | Toronto, ON, Canada
Machine Learning/DevOps Engineer II
@ Extend | Remote, United States
Business Intelligence Developer, Marketing team (Bangkok based, relocation provided)
@ Agoda | Bangkok (Central World)