Facebook AI & JHU’s MaskFeat Method Surpasses Kaiming He’s MAE, Sets New SOTA in Video Action Recognition
In the new paper Masked Feature Prediction for Self-Supervised Visual Pre-Training, a Facebook AI Research and Johns Hopkins University team presents a novel Masked Feature Prediction (MaskFeat) ap...
Source: syncedreview.com
In the new paper Masked Feature Prediction for Self-Supervised Visual Pre-Training, a Facebook AI Research and Johns Hopkins University team presents a novel Masked Feature Prediction (MaskFeat) approach for the self-supervised pretraining of video models that achieves SOTA results on video benchmarks.