Generating Natural Questions from Images for Multimodal Assistants
Open accessAbstract
Generating natural, diverse, and meaningful questions from images is an essential task for multimodal assistants as it confirms whether they have understood the object and scene in the images properly. The research in visual question answering (VQA) and visual question generation (VQG) is a great step. However, this research does not capture questions that a visually-abled person would ask multimodal assistants. Recently published datasets such as KB-VQA, FVQA, and OK-VQA try to collect questions that look for external knowledge which makes them appropriate for multimodal assistants. However, they still contain many obvious and common-sense questions that humans would not usually ask a digital assistant. In this paper, we provide a new benchmark dataset that contains questions generated by human annotators keeping in mind what they would ask multimodal digital assistants. Large scale annotations for thousands of images are expensive and time-consuming, so we also present an effective way of automatically generating questions from unseen images. In this paper, we present an approach for generating diverse and meaningful questions that consider image content and metadata of image (e.g., location, associated keyword). We evaluate our approach using standard evaluation metrics such as BLEU, METEOR, ROUGE, and CIDEr to show the relevance of generated questions with human-provided questions. We also measure the diversity of generated questions using generative strength and inventiveness metrics. We report new state-of-the-art results on the public and our datasets.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Using multiple modalities can target more real-world applications, including educational questions based on pictures and diagrams and helping visually challenged people identify objects.
“Using multiple modalities, more real-world applications can be targeted, including generating questions based on pictures and diagrams in educational domain [126] and helping the visually challenged identify objects around them [127].”
From Automatic question generation: a review of methodologies, datasets, evaluation metrics, and applications (2023) · cites this paper as [127]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566 · see citing works
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · see citing works
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015 · see citing works
Show and tell: A neural image caption generator
Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298935 · Cited by 6,318 · see citing works
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
Lu, J., Batra, D., Parikh, D., & Lee, S. (2019) · arXiv · doi:10.48550/arxiv.1908.02265 · Cited by 2,109 · see citing works
Ask Your Neurons: A Neural-Based Approach to Answering Questions about Images
Malinowski, M., Rohrbach, M., & Fritz, M. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.9 · Cited by 633 · see citing works
VQA: Visual Question Answering: www.visualqa.org
Agrawal, A., Lu, J., Antol, S., Mitchell, M., Zitnick, C. L., Parikh, D., & Batra, D. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-016-0966-6 · Cited by 570 · see citing works
FVQA: Fact-Based Visual Question Answering
Wang, P., Wu, Q., Shen, C., Dick, A., & van den Hengel, A. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2754246 · Cited by 490 · see citing works
Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question AnsweringPreprint
Gao, H., Mao, J., Zhou, J., Huang, Z., Wang, L., & Xu, W. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.05612 · Cited by 437 · see citing works
Ask Me Anything: Free-Form Visual Question Answering Based on Knowledge from External Sources
Wu, Q., Wang, P., Shen, C., Dick, A., & van den Hengel, A. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.500 · Cited by 362 · see citing works
VL-BERT: Pre-training of Generic Visual-Linguistic Representations
Su, W., Zhu, X., Cao, Y., Li, B., Lu, L., Wei, F., & Dai, J. (2020) · International Conference on Learning Representations · Cited by 276 · see citing works
Generating Natural Questions About an Image
Mostafazadeh, N., Misra, I., Devlin, J., Mitchell, M., He, X., & Vanderwende, L. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1170 · Cited by 270 · see citing works
Measuring the Effects of Data Parallelism on Neural Network Training
Shallue, C. J., Lee, J., Antognini, J., Sohl-Dickstein, J., Frostig, R., & Dahl, G. E. (2018) · arXiv · doi:10.48550/arxiv.1811.03600 · Cited by 229 · see citing works
Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question AnsweringPreprint
Narasimhan, M., Lazebnik, S., & Schwing, A. G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.00538 · Cited by 184 · see citing works
Ask Your Neurons: A Neural-based Approach to Answering Questions about ImagesPreprint
Malinowski, M., Rohrbach, M., & Fritz, M. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.01121 · Cited by 181 · see citing works
Creativity: Generating Diverse Questions Using Variational Autoencoders
Jain, U., Zhang, Z., & Schwing, A. G. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.575 · Cited by 131 · see citing works
Automatic Generation of Grounded Visual Questions
Zhang, S., Qu, L., You, S., Yang, Z., & Zhang, J. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/592 · Cited by 82 · see citing works
Shahbaz, M., Suresh, L., Rexford, J., et al. (2019) · doi:10.1145/3341302.3342066 · Cited by 53 · see citing works
Creativity: Generating Diverse Questions using Variational AutoencodersPreprint
Jain, U., Zhang, Z., & Schwing, A. G. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.03493 · Cited by 32 · see citing works
Automatic Generation of Grounded Visual QuestionsPreprint
Zhang, S., Qu, L., You, S., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.06530 · Cited by 11 · see citing works
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805
Flagged first, then by citations
Research works printed but not linked: 9
- Wang, P., Wu, Q., Shen, C., Dick, A., & Van Den Hengel, A. (2017). KB-VQA Explicit knowledge-based reasoning for visual question answering. IJCAI Interna- tional Joint Conference on Artificial Intelligence, 1290-1296. https://doi.org/10.24963/ijcai.2017/179 · DOI
- Marino, K., Rastegari, M., Farhadi, A., & Mottaghi, R. (2019). OK-VQA: A Visual Question Answering Bench- mark Requiring External Knowledge. Retrieved from http://arxiv.org/abs/1906.00067 · arXiv
- Simonyan, K., & Zisserman, A. (2015). Very deep convolu- tional networks for large-scale image recognition. 3rd Interna- tional Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings.
- Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. Proceedings -30th IEEE Conference on Computer Vision and Pattern Recog- nition, CVPR 2017.
- Ren, M., Kiros, R., & Zemel, R. (2015). Exploring Mod- els and Data for Image Question Answering. Advances in Neural Information Processing Systems. Retrieved from http://arxiv.org/abs/1505.02074 · arXiv
- Marino, K., Rastegari, M., Farhadi, A., & Mottaghi, R. (2019). OK-VQA: A Visual Question Answering Bench- mark Requiring External Knowledge. Retrieved from http://arxiv.org/abs/1906.00067 · arXiv
- Simonyan, K., & Zisserman, A. (2015). Very deep convolu- tional networks for large-scale image recognition. 3rd Interna- tional Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings.
- Vijayakumar, A. K., Cogswell, M., Selvaraju, R. R., Sun, Q., Lee, S., Crandall, D., & Batra, D. (2016). Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models. 1-16. Retrieved from http://arxiv.org/abs/1610.02424 · arXiv
- Li, G., Duan, N., Fang, Y., Gong, M., Jiang, D., & Zhou, M. (2019). Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training. Retrieved from http://arxiv.org/abs/1908.06066 · arXiv
Cited by
Sorted by citations
Mulla, N., & Gharpure, P. (2023) · Progress in Artificial Intelligence · doi:10.1007/s13748-023-00295-9 · Cited by 132 · see citing works
- Authors
- Patel, A., Bindal, A., Kotek, H., Klein, C., & Williams, J.
- Affiliations
- Apple (United States) (US)
- Venue
- ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2021-06-06
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W3116613428
- Cited by
- 6
- References
- 22
- Citations by year
- 2025: 1 · 2024: 2 · 2023: 2 · 2022: 1
- FWCI
- 0.41
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- IEEE RESOURCE CENTERS
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- visual question generation, benchmark dataset, image metadata, question diversity, visual question answering
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
