Focal Interest
Focal Interest

Transformer

  1. Binarized MLP-Mixer trained successfully on MNIST
    Binarized MLP-Mixer achieves 0.9+ accuracy with quantized activations on MNIST, enabling efficient deployment on IoT edge devices without convolutional or attention mechanisms.
  2. Data augmented hybrid GCN transformer for student engagement recognition in E-learning
    Hybrid framework combining graph networks and transformers with synthetic data augmentation for automatic student engagement recognition from facial video in e-learning systems.