Unsupervised optical flow estimation is especially hard near occlusions ...
Unsupervised optical flow estimators based on deep learning have attract...
We propose TAIN (Transformers and Attention for video INterpolation), a
...
Recently, one-stage trackers that use a joint model to predict both
dete...
Supervised training of optical flow predictors generally yields better
a...
We propose MONet, a convolutional neural network that jointly detects mo...
Residual Neural Networks (ResNets) achieve state-of-the-art performance ...