CVPR 2020

Transform and Tell: Entity-Aware News Image Captioning

Nov 12, 2020

|

46 views

|

Alasdair Tran

Multi-Head Attention

Details

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

Category: CVPR 2020

Comments

loading...

Reactions (0) | Note

📝 No reactions yet

Be the first one to share your thoughts!

Reactions(0)

Note

loading...

Recommended

ICAPS 2014: Christopher Expósito-Izquierdo on "Optimization Model and Heuristic Approach for ..."

ICAPS | Apr 16, 2015

ICAPS 2014: Iman Awaad on "Finding Ways to Get the Job Done: An Affordance-Based Approach"

ICAPS | Apr 20, 2015

ICAPS 2014 Invited Talk by Malik Ghallab

ICAPS | May 4, 2015

ICAPS 2014: Steven Levine on "Concurrent Plan Recognition and Execution for Human-Robot Teams"

ICAPS | May 4, 2015

ICAPS 2014: Peng Yu on "Resolving Uncontrollable Conditional Temporal Problems Using ..."

ICAPS | May 4, 2015