Search Results for author:
Found 3 papers, 3 papers with code
Neural-Hidden-CRF: A Robust Weakly-Supervised Sequence Labeler
In Neural-Hidden-CRF, we can capitalize on the powerful language model BERT or other deep models to provide rich contextual semantic knowledge to the latent ground truth sequence, and use the hidden CRF layer to capture the internal label dependencies.
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential
Next, we construct a graph convolution training acceleration mechanism to optimize the back-propagation computing of dynamic graph learning with 55. 08\% speed-up.
Ranked #3 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Learning from Noisy Crowd Labels with Logics
This paper explores the integration of symbolic logic knowledge into deep neural networks for learning from noisy crowd labels.
