Name: Transform and Tell: Entity-Aware News Image Captioning (CVPR 2020)
Uploaded: 2021-03-24T23:16:25Z
Duration: 1 min 1 s
Description: We propose an end-to-end model which generates captions for images embedded in news articles. Our model outperforms the previous state of the art by a factor of four in CIDEr score. Paper: https://ar...

We propose an end-to-end model which generates captions for images embedded in news articles. Our model outperforms the previous state of the art by a factor of four in CIDEr score.

Paper: https://arxiv.org/abs/2004.08070
Demo: https://transform-and-tell.ml/
Code: https://github.com/alasdairtran/transform-and-tell

Acknowledgement:
The background music is from https://www.bensound.com

Multi-Head Attention

CVPR 2020

Transform and Tell: Entity-Aware News Image Captioning (CVPR 2020)

Alasdair Tran

Details

Comments

Recommended