1. Trocr: Transformer-based optical character recognition with pre-trained models;li,2021
2. Convolutional MKL Based Multimodal Emotion Recognition and Sentiment Analysis
3. Supervised multimodal bitransformers for classifying images and text;kiela,2019
4. Edge-Gan: Edge Conditioned Multi-View Face Image Generation
5. Bert: Pre-training of deep bidirectional transformers for language understanding;devlin,2018