Search Results for author:
Found 3 papers, 0 papers with code
Uncertainty-aware Action Decoupling Transformer for Action Anticipation
The objective is to make the two decoupled tasks assist each other and eventually improve the action anticipation task.
Ranked #1 on
Action Anticipation
on 50-Salads
Physics-Augmented Autoencoder for 3D Skeleton-Based Gait Recognition
During the inference, the decoder is discared and a RNN-based classifier takes the output of the encoder for gait recognition.
Uncertainty-Guided Probabilistic Transformer for Complex Action Recognition
The model prediction uncertainty is used to improve both training and inference.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
