CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images

Shailaja Keyur Sampat, Akshay Kumar, Yezhou Yang, Chitta Baral


Abstract
Most existing research on visual question answering (VQA) is limited to information explicitly present in an image or a video. In this paper, we take visual understanding to a higher level where systems are challenged to answer questions that involve mentally simulating the hypothetical consequences of performing specific actions in a given scenario. Towards that end, we formulate a vision-language question answering task based on the CLEVR (Johnson et. al., 2017) dataset. We then modify the best existing VQA methods and propose baseline solvers for this task. Finally, we motivate the development of better vision-language models by providing insights about the capability of diverse architectures to perform joint reasoning over image-text modality. Our dataset setup scripts and codes will be made publicly available at https://github.com/shailaja183/clevr_hyp.
Anthology ID:
2021.naacl-main.289
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3692–3709
Language:
URL:
https://aclanthology.org/2021.naacl-main.289
DOI:
10.18653/v1/2021.naacl-main.289
Bibkey:
Cite (ACL):
Shailaja Keyur Sampat, Akshay Kumar, Yezhou Yang, and Chitta Baral. 2021. CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3692–3709, Online. Association for Computational Linguistics.
Cite (Informal):
CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images (Sampat et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.289.pdf
Optional supplementary data:
 2021.naacl-main.289.OptionalSupplementaryData.pdf
Code
 shailaja183/clevr_hyp
Data
CLEVRRACESHAPESTQAVCRVisual Question Answering