Search Results for author:
Found 2 papers, 0 papers with code
Building a Bridge: A Method for Image-Text Sarcasm Detection Without Pretraining on Image-Text Data
We use the pretrained Multi-Head Attention of BERT to model the text and image.
Teaching Text-to-Image Models to Communicate in Dialog
In this paper, we focus on the innovative dialog-to-image generation task, where the model synthesizes a high-resolution image aligned with the given dialog context as a response.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
