Engaging Image Captioning Via Personality

CVPR, Volume abs/1810.10665, 2019, Pages 12516-12526.

Cited by: 21|Bibtex|Views175
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Standard image captioning tasks such as COCO and Flickr30k are factual, neutral in tone and (to a human) state the obvious (e.g., "a man playing a guitar"). While such tasks are useful to verify that a machine understands the content of an image, they are not engaging to humans as captions. With this in mind we define a new task, Person...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments