Continually learning new skills is important for intelligent systems, yet standard deep learning methods suffer from catastrophic forgetting of the past.
If the initial image is not well initialized, the following processes can hardly refine the image to a satisfactory quality.
Ranked #3 on Text-to-Image Generation on COCO (SOA-C metric)
In this work, we propose to refine the predictions of structured prediction models by effectively integrating discriminative models into the prediction.
In this paper, we propose a new approach, namely Hierarchical Recurrent Neural Encoder (HRNE), to exploit temporal information of videos.