Image-Set Visual Question Answering

Ankan Bansal, Yuting Zhang, and Rama Chellappa

Fig. 1: Some examples from our ISVQA dataset.

Abstract: We introduce the task of Image-Set Visual Question Answering (ISVQA), which generalizes the commonly studied single-image VQA problem to multi-image settings. Taking a natural language question and a set of images as input, it aims to answer the question based on the contents of the images. The questions can be about objects and relationships in one or more images or about the entire scene depicted by the image set. To enable research on this new topic, we introduce two ISVQA datasets - indoor and outdoor scenes. They simulate the real-world scenarios of indoor image collections and multiple car-mounted cameras, respectively. The indoor-scene dataset contains 91,479 human-annotated questions for 48,138 image sets, and the outdoor-scene dataset has 49,617 questions for 12,746 image sets. We analyze the properties of the two datasets, including question-and-answer distributions, types of questions, biases in the dataset, and question-image dependencies. We also build new baseline models to investigate new research challenges in ISVQA.


Our datasets and more details can be found here.


Our paper is available here.

If you use the datasets, please cite our paper using the bibtex:

    author = {Bansal, Ankan and Zhang, Yuting and Chellappa, Rama},
    title = {Visual Question Answering on Image Sets},
    booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
    year = {2020},