Multi-Gate Attention Network for Image Captioning
Self-attention mechanism, which has been successfully applied to current encoder-decoder framework of image captioning, is used to enhance the feature representation in the image encoder and capture the most relevant information for the language decoder. However, most existing methods will assign at...
| Main Authors: | , , , , |
|---|---|
| פורמט: | Article |
| שפה: | English |
| יצא לאור: |
IEEE
2021-01-01
|
| סדרה: | IEEE Access |
| נושאים: | |
| גישה מקוונת: | https://ieeexplore.ieee.org/document/9382255/ |