CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images
This work addresses a limitation in VQA research by enabling reasoning about hypothetical scenarios, which is incremental as it builds on the CLEVR dataset and existing methods.
The paper tackles the problem of visual question answering (VQA) by introducing a new dataset, CLEVR_HYP, that requires systems to simulate hypothetical actions in images, and they propose baseline solvers by modifying existing VQA methods, achieving initial results that highlight the challenge of this task.
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.