Skip navigation
Please use this identifier to cite or link to this item:
Title: CLEVR-Matrices
Contributors: Mondal, Shanka Subhra
Webb, Taylor
Cohen, Jonathan
Keywords: CLEVR, RPM, abstract visual reasoning
Issue Date: 1-Mar-2023
Publisher: Princeton University
Abstract: A dataset of Raven’s Progressive Matrices (RPM)-like problems using realistically rendered 3D shapes, based on source code from CLEVR (a popular visual-question-answering dataset) (Johnson, J., Hariharan, B., Van Der Maaten, L., Fei-Fei, L., Lawrence Zitnick, C., & Girshick, R. (2017). Clevr: A diagnostic dataset for compositional language and elementary visual reasoning. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2901-2910)).
Description: Download the README.txt file for a detailed description of this dataset's content; This dataset is too large to download directly from this item page. You can access and download the data via Globus at this link: [] (See for instructions on how to use Globus; sign-in is required).
Appears in Collections:Research Data Sets

Files in This Item:
File Description SizeFormat 
README.txt3.05 kBTextView/Download

Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.