Skip to content

"Describing Textures using Natural Language" code and data, ECCV 2020 Oral.

Notifications You must be signed in to change notification settings

ChenyunWu/DescribingTextures

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

This is the repo for the ECCV 2020 paper "Describing Textures using Natural Language".
More contents are shared on the project webpage.

Our collected annotations are in data_api/data/image_desciptions.json. data_api includes all basic data handling code. DTD images should be put under data_api/data/images. They can be downloaded from the DTD website.

Code for training and evaluating 3 baseline models are under models/naive_classifier/, models/show_attend_tell/, models/triplet_match respectively. We also include additional application and visualization code.

More documentation will be added to this repo. Feel free to contact chenyun _AT_ cs.umass.edu if you have any questions.

About

"Describing Textures using Natural Language" code and data, ECCV 2020 Oral.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published