Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

By Kosuke Futamata, Mon 11 June 2018, in category Cv

Attention, IDG

1. どんなもの?

2. 先行研究と比べてどこがすごいの?

3. 技術や手法の"キモ"はどこにある?

4. どうやって有効だと検証した?

5. 議論はあるか?

6. 次に読むべき論文はあるか?

論文情報・リンク

https://github.com/kelvinxu/arctic-captions

Articles connexes

Thu 26 July 2018
Rich Image Captioning in the Wild
Mon 23 July 2018
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Mon 02 July 2018
SemStyle: Learning to Generate Stylised Image Captions using Unaligned Text