# Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering

arXiv: https://arxiv.org/abs/2306.16713 · HTML: https://mlsanity.com/paper/2306.16713/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 58 references that are in the map.
- First posted on arXiv 29 Jun 2023.

## Builds on (most cited first, 30 of 46)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [SimVLM: Simple Visual Language Model Pretraining with Weak Supervision](https://mlsanity.com/paper/2108.10904/) (2021)
- [Unified Vision-Language Pre-Training for Image Captioning and VQA](https://mlsanity.com/paper/1909.11059/) (2019)
- [TVQA: Localized, Compositional Video Question Answering](https://mlsanity.com/paper/1809.01696/) (2018)
- [A Corpus for Reasoning About Natural Language Grounded in Photographs](https://mlsanity.com/paper/1811.00491/) (2018)
- [Unifying Vision-and-Language Tasks via Text Generation](https://mlsanity.com/paper/2102.02779/) (2021)
- [Neural Module Networks](https://mlsanity.com/paper/1511.02799/) (2015)
- [Visual7W: Grounded Question Answering in Images](https://mlsanity.com/paper/1511.03416/) (2015)
- [MovieQA: Understanding Stories in Movies through Question-Answering](https://mlsanity.com/paper/1512.02902/) (2015)
- [Hierarchical Question-Image Co-Attention for Visual Question Answering](https://mlsanity.com/paper/1606.00061/) (2016)
- [12-in-1: Multi-Task Vision and Language Representation Learning](https://mlsanity.com/paper/1912.02315/) (2019)
- [Stacked Attention Networks for Image Question Answering](https://mlsanity.com/paper/1511.02274/) (2015)

## Built on by (most cited first, 10 of 10)

- [Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark](https://mlsanity.com/paper/2407.13766/) (2024)
- [Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents](https://mlsanity.com/paper/2411.16740/) (2024)
- [Step Differences in Instructional Video](https://mlsanity.com/paper/2404.16222/) (2024)
- [MultiHaystack: Benchmarking Multimodal Retrieval and Reasoning over 40K Images, Videos, and Documents](https://mlsanity.com/paper/2603.05697/) (2026)
- [Audiopedia: Audio QA with Knowledge](https://mlsanity.com/paper/2412.20619/) (2024)
- [GoldiCLIP: The Goldilocks Approach for Balancing Explicit Supervision for Language-Image Pretraining](https://mlsanity.com/paper/2603.24804/) (2026)
- [Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity](https://mlsanity.com/paper/2606.25343/) (2026)
- [CHaystack: Benchmarking Chinese Document Retrieval and VQA](https://mlsanity.com/paper/2607.24760/) (2026)
- [ReToken: One Token to Improve Vision-Language Models for Visual Retrieval](https://mlsanity.com/paper/2607.28627/) (2026)
- [CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Generation](https://mlsanity.com/paper/2609.05518/) (2026)

## Abstract (arXiv)

We study visual question answering in a setting where the answer has to be mined from a pool of relevant and irrelevant images given as a context. For such a setting, a model must first retrieve relevant images from the pool and answer the question from these retrieved images. We refer to this problem as retrieval-based visual question answering (or RETVQA in short). The RETVQA is distinctively different and more challenging than the traditionally-studied Visual Question Answering (VQA), where a given question has to be answered with a single relevant image in context. Towards solving the RETVQA task, we propose a unified Multi Image BART (MI-BART) that takes a question and retrieved images using our relevance encoder for free-form fluent answer generation. Further, we introduce the largest dataset in this space, namely RETVQA, which has the following salient features: multi-image and retrieval requirement for VQA, metadata-independent questions over a pool of heterogeneous images, expecting a mix of classification-oriented and open-ended generative answers. Our proposed framework achieves an accuracy of 76.5% and a fluency of 79.3% on the proposed dataset, namely RETVQA and also outperforms state-of-the-art methods by 4.9% and 11.8% on the image segment of the publicly available WebQA dataset on the accuracy and fluency metrics, respectively.