This dataset is designed to advance research in Visual Question Answering (VQA), specifically addressing challenges related to language priors and compositional reasoning. It incorporates question labels categorizing queries based on their susceptibility to either issue, allowing for targeted evaluation of VQA models. The dataset consists of 33,051 training images and 14,165 validation images, along with 571,244 training questions and 245,087 validation questions. Among the training questions, 313,664 focus on compositional reasoning, while 257,580 pertain to language prior.

DOI Link: 
10.21227/9cjm-dx19
Read more

Dataset Files

You must be an IEEE Dataport Subscriber to access these files. Subscribe now or login.

[1] Souvik Chowdhury, Badal Soni, " Robust VQA (RVQA) Dataset with Language Prior and Compositional Reasoning Labels", IEEE Dataport, 2024. [Online]. Available: http://dx.doi.org/10.21227/9cjm-dx19. Accessed: Feb. 10, 2025.
@data{9cjm-dx19-24,
doi = {10.21227/9cjm-dx19},
url = {http://dx.doi.org/10.21227/9cjm-dx19},
author = {Souvik Chowdhury; Badal Soni },
publisher = {IEEE Dataport},
title = { Robust VQA (RVQA) Dataset with Language Prior and Compositional Reasoning Labels},
year = {2024} }
TY - DATA
T1 - Robust VQA (RVQA) Dataset with Language Prior and Compositional Reasoning Labels
AU - Souvik Chowdhury; Badal Soni
PY - 2024
PB - IEEE Dataport
UR - 10.21227/9cjm-dx19
ER -
Souvik Chowdhury, Badal Soni. (2024). Robust VQA (RVQA) Dataset with Language Prior and Compositional Reasoning Labels. IEEE Dataport. http://dx.doi.org/10.21227/9cjm-dx19
Souvik Chowdhury, Badal Soni, 2024. Robust VQA (RVQA) Dataset with Language Prior and Compositional Reasoning Labels. Available at: http://dx.doi.org/10.21227/9cjm-dx19.
Souvik Chowdhury, Badal Soni. (2024). " Robust VQA (RVQA) Dataset with Language Prior and Compositional Reasoning Labels." Web.
1. Souvik Chowdhury, Badal Soni. Robust VQA (RVQA) Dataset with Language Prior and Compositional Reasoning Labels [Internet]. IEEE Dataport; 2024. Available from : http://dx.doi.org/10.21227/9cjm-dx19
Souvik Chowdhury, Badal Soni. " Robust VQA (RVQA) Dataset with Language Prior and Compositional Reasoning Labels." doi: 10.21227/9cjm-dx19