[project page] [paper]
If this code helps with your work, please cite:
Rohit Girdhar and Deva Ramanan. CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning. In International Conference on Learning Representations (ICLR), 2020.
@inproceedings{girdhar2020cater,
title = {{CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning}},
author = {Girdhar, Rohit and Ramanan, Deva},
booktitle = {ICLR},
year = 2020
}A pre-generated sample of the dataset used in the paper is provided here (direct download links here). If you'd like to generate a version of the dataset, please follow instructions in generate.
We provide code and some basic instructions on setting up some of the baselines in baselines folder.
This code was built upon the CLEVR codebase and various video recognition codebases for baselines (especially Non-Local). Many thanks to those authors for making their code available!
CATER is Apache 2.0 licensed, as found in the LICENSE file.