# Survey of Visual Question Answering: Datasets and Techniques

arXiv: https://arxiv.org/abs/1705.03865 · HTML: https://mlsanity.com/paper/1705.03865/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2017.

## Built on by (most cited first, 9 of 9)

- [Biomedical Question Answering: A Survey of Approaches and Challenges](https://mlsanity.com/paper/2102.05281/) (2021)
- [From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities](https://mlsanity.com/paper/2311.00308/) (2023)
- [Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices](https://mlsanity.com/paper/2112.03572/) (2021)
- [EVJVQA Challenge: Multilingual Visual Question Answering](https://mlsanity.com/paper/2302.11752/) (2023)
- [COIN: Counterfactual Image Generation for VQA Interpretation](https://mlsanity.com/paper/2201.03342/) (2022)
- [Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions](https://mlsanity.com/paper/2211.02646/) (2022)
- [A Generative Approach for Mitigating Structural Biases in Natural Language Inference](https://mlsanity.com/paper/2108.14006/) (2021)
- [VisionTrap: Unanswerable Questions On Visual Data](https://mlsanity.com/paper/2507.17262/) (2025)
- [BodyCam-VQA: Enhanced Body-Worn Camera Video Captioning via Multimodal Reasoning and Probe Question Generation](https://mlsanity.com/paper/2609.10815/) (2026)

## Abstract (arXiv)

Visual question answering (or VQA) is a new and exciting problem that combines natural language processing and computer vision techniques. We present a survey of the various datasets and models that have been used to tackle this task. The first part of the survey details the various datasets for VQA and compares them along some common factors. The second part of this survey details the different approaches for VQA, classified into four types: non-deep learning models, deep learning models without attention, deep learning models with attention, and other models which do not fit into the first three. Finally, we compare the performances of these approaches and provide some directions for future work.