# iVQA: Inverse Visual Question Answering

arXiv: https://arxiv.org/abs/1710.03370 · HTML: https://mlsanity.com/paper/1710.03370/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Oct 2017.

## Built on by (most cited first, 22 of 22)

- [EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding](https://mlsanity.com/paper/2308.09126/) (2023)
- [SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models](https://mlsanity.com/paper/2406.01584/) (2024)
- [AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark](https://mlsanity.com/paper/2410.03051/) (2024)
- [Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs](https://mlsanity.com/paper/2406.09367/) (2024)
- [From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities](https://mlsanity.com/paper/2311.00308/) (2023)
- [Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQA](https://mlsanity.com/paper/2211.07516/) (2022)
- [Long Story Short: Story-level Video Understanding from 20K Short Films](https://mlsanity.com/paper/2406.10221/) (2024)
- [K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisition](https://mlsanity.com/paper/2203.07890/) (2022)
- [Towards Artwork Explanation in Large-scale Vision Language Models](https://mlsanity.com/paper/2403.00068/) (2024)
- [The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training](https://mlsanity.com/paper/2205.12502/) (2022)
- [Towards Cross-Lingual Explanation of Artwork in Large-scale Vision Language Models](https://mlsanity.com/paper/2409.01584/) (2024)
- [End-to-End Video Question-Answer Generation with Generator-Pretester Network](https://mlsanity.com/paper/2101.01447/) (2021)
- [A Survey on Neural Question Generation: Methods, Applications, and Prospects](https://mlsanity.com/paper/2402.18267/) (2024)
- [Learning by Asking Questions for Knowledge-based Novel Object Recognition](https://mlsanity.com/paper/2210.05879/) (2022)
- [Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question Generation](https://mlsanity.com/paper/2401.10005/) (2024)
- [ECIS-VQG: Generation of Entity-centric Information-seeking Questions from Videos](https://mlsanity.com/paper/2410.09776/) (2024)
- [Cin'easte: A Fine-grained Contextual Movie Question Answering Benchmark](https://mlsanity.com/paper/2509.14227/) (2025)
- [Ask Questions with Double Hints: Visual Question Generation with Answer-awareness and Region-reference](https://mlsanity.com/paper/2407.05100/) (2024)
- [Performance Analysis of Traditional VQA Models Under Limited Computational Resources](https://mlsanity.com/paper/2502.05738/) (2025)
- [Meaning Versus Information, Prediction Versus Memory, and Question Versus Answer](https://mlsanity.com/paper/2107.13393/) (2021)
- [Enhanced Textual Feature Extraction for Visual Question Answering: A Simple Convolutional Approach](https://mlsanity.com/paper/2405.00479/) (2024)
- [VideoChain: A Transformer-Based Framework for Multi-hop Video Question Generation](https://mlsanity.com/paper/2511.08348/) (2025)

## Abstract (arXiv)

We propose the inverse problem of Visual question answering (iVQA), and explore its suitability as a benchmark for visuo-linguistic understanding. The iVQA task is to generate a question that corresponds to a given image and answer pair. Since the answers are less informative than the questions, and the questions have less learnable bias, an iVQA model needs to better understand the image to be successful than a VQA model. We pose question generation as a multi-modal dynamic inference process and propose an iVQA model that can gradually adjust its focus of attention guided by both a partially generated question and the answer. For evaluation, apart from existing linguistic metrics, we propose a new ranking metric. This metric compares the ground truth question's rank among a list of distractors, which allows the drawbacks of different algorithms and sources of error to be studied. Experimental results show that our model can generate diverse, grammatically correct and content correlated questions that match the given answer.