A Dynamic Memory Network is a neural network architecture which processes input sequences and questions, forms episodic memories, and generates relevant answers. Questions trigger an iterative attention process which allows the model to condition its attention on the inputs and the result of previous iterations. These results are then reasoned over in a hierarchical recurrent sequence model to generate answers.
The DMN consists of a number of modules:
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Question Answering | 4 | 10.00% |
Semantic Segmentation | 3 | 7.50% |
Video Object Segmentation | 3 | 7.50% |
Video Semantic Segmentation | 3 | 7.50% |
Semi-Supervised Video Object Segmentation | 2 | 5.00% |
Template Matching | 2 | 5.00% |
Visual Tracking | 2 | 5.00% |
Visual Question Answering (VQA) | 2 | 5.00% |
Semantic Parsing | 1 | 2.50% |