Awesome
Cops-Ref: A new Dataset and Task on Compositional Referring Expression Comprehension
This repo contains the Cops-Ref dataset and the main baseline. Please refer to our paper for more information.
An example
<p align="center"> <figcaption> <strong> Expression</strong>: "The cat on the left that is sleeping and resting on the white towel."<strong>Reasoning tree</strong>: cat (left, sleeping) towel.
</figcaption> </p> <p align="center"> <img src="images/example.jpg" alt="architecture" width="700px"> </p>Contents
Dataset
We provide the annotation of the dataset at OneDrive. Please read this for details of the annotation.
Citing Cops-Ref
If you find this repo useful in your research, please consider citing:
@inroceedings{Chen_2020_CVPR,
author = {Chen, Zhenfang and Wang, Peng and Ma, Lin and Wong, Kwan-Yee~K. and Wu, Qi},
title = {Cops-Ref: A New Dataset and Task on Compositional Referring Expression Comprehension},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}
Contact
You can contact Zhenfang Chen by sending email to chenzhenfang2013@gmail.com