Search Results for author:
Found 2 papers, 2 papers with code
Unsupervised hard Negative Augmentation for contrastive learning
We present Unsupervised hard Negative Augmentation (UNA), a method that generates synthetic negative instances based on the term frequency-inverse document frequency (TF-IDF) retrieval model.
Revisiting Self-Supervised Contrastive Learning for Facial Expression Recognition
The success of most advanced facial expression recognition works relies heavily on large-scale annotated datasets.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
