Visual Question Answering (VQA)

Visual Question Answering (VQA) is a task in computer vision that involves answering questions about an image. The goal of VQA is to teach machines to understand the content of an image and answer questions about it in natural language.

Image Source: visualqa.org

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 801–825 of 2167 papers

Title	Date	Tasks	Status	Score
From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models	Dec 21, 2022	Question AnsweringVisual Question Answering	CodeCode Available	5
ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering	Jun 6, 2019	Question AnsweringVideo Question Answering	CodeCode Available	5
MUREL: Multimodal Relational Reasoning for Visual Question Answering	Feb 25, 2019	Relational ReasoningVisual Question Answering	CodeCode Available	5
FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering	May 27, 2025	BenchmarkingQuestion Answering	CodeCode Available	5
ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images	Feb 9, 2025	Clinical KnowledgeMedical Visual Question Answering	CodeCode Available	5
Modulating early visual processing by language	Jul 2, 2017	Question AnsweringVisual Question Answering	CodeCode Available	5
CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions	Jan 3, 2019	DiagnosticImage Segmentation	CodeCode Available	5
Focal Visual-Text Attention for Visual Question Answering	Jun 5, 2018	Memex Question AnsweringQuestion Answering	CodeCode Available	5
CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering	Nov 7, 2022	Add - POAdd - PQ	CodeCode Available	5
QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning	May 6, 2022	DiagnosticQuestion Answering	CodeCode Available	5
Modeling Relationships in Referential Expressions with Compositional Modular Networks	Nov 30, 2016	Visual Question Answering (VQA)	CodeCode Available	5
Focal Visual-Text Attention for Memex Question Answering	Dec 14, 2018	Memex Question AnsweringQuestion Answering	CodeCode Available	5
CLEVR\_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images	Jun 1, 2021	Question AnsweringVisual Question Answering	CodeCode Available	5
Modularized Zero-shot VQA with Pre-trained Models	May 27, 2023	object-detectionObject Detection	CodeCode Available	5
CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images	Apr 13, 2021	Question AnsweringVisual Question Answering	CodeCode Available	5
ArtQuest: Countering Hidden Language Biases in ArtVQA	Jan 4, 2024	Question AnsweringVisual Question Answering	CodeCode Available	5
HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation	May 16, 2025	BenchmarkingEthics	CodeCode Available	5
CLEAR: A Dataset for Compositional Language and Elementary Acoustic Reasoning	Nov 26, 2018	Acoustic Question AnsweringQuestion Answering	CodeCode Available	5
Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic Approach	Oct 3, 2022	Referring ExpressionRobot Manipulation	CodeCode Available	5
MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering	Nov 1, 2021	multimodal interactionMultiple-choice	CodeCode Available	5
II-MMR: Identifying and Improving Multi-modal Multi-hop Reasoning in Visual Question Answering	Feb 16, 2024	Question AnsweringTriplet	CodeCode Available	5
ILLUME: Rationalizing Vision-Language Models through Human Interactions	Aug 17, 2022	Image CaptioningQuestion Answering	CodeCode Available	5
Filling the Image Information Gap for VQA: Prompting Large Language Models to Proactively Ask Questions	Nov 20, 2023	Question AnsweringVisual Question Answering	CodeCode Available	5
FigureQA: An Annotated Figure Dataset for Visual Reasoning	Oct 19, 2017	BIG-bench Machine LearningChart Question Answering	CodeCode Available	5
Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering	May 21, 2015	Question AnsweringSentence	CodeCode Available	5

Show:10 25 50

← PrevPage 33 of 87Next →

All datasets GQA Test2019 VQA v2 test-dev VQA v2 test-std OK-VQA MSVD-QA DocVQA test MSRVTT-QA InfographicVQA GQA test-dev VizWiz 2020 VQA A-OKVQA CLEVR

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	human	Accuracy	89.3	—	Unverified
2	DREAM+Unicoder-VL (MSRA)	Accuracy	76.04	—	Unverified
3	TRRNet (Ensemble)	Accuracy	74.03	—	Unverified
4	MIL-nbgao	Accuracy	73.81	—	Unverified
5	Kakao Brain	Accuracy	73.33	—	Unverified
6	Coarse-to-Fine Reasoning, Single Model	Accuracy	72.14	—	Unverified
7	270	Accuracy	70.23	—	Unverified
8	NSM ensemble (updated)	Accuracy	67.55	—	Unverified
9	VinVL-DPT	Accuracy	64.92	—	Unverified
10	VinVL+L	Accuracy	64.85	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	PaLI	Accuracy	84.3	—	Unverified
2	BEiT-3	Accuracy	84.19	—	Unverified
3	VLMo	Accuracy	82.78	—	Unverified
4	ONE-PEACE	Accuracy	82.6	—	Unverified
5	mPLUG (Huge)	Accuracy	82.43	—	Unverified
6	CuMo-7B	Accuracy	82.2	—	Unverified
7	X2-VLM (large)	Accuracy	81.9	—	Unverified
8	MMU	Accuracy	81.26	—	Unverified
9	Lyrics	Accuracy	81.2	—	Unverified
10	InternVL-C	Accuracy	81.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BEiT-3	overall	84.03	—	Unverified
2	mPLUG-Huge	overall	83.62	—	Unverified
3	ONE-PEACE	overall	82.52	—	Unverified
4	X2-VLM (large)	overall	81.8	—	Unverified
5	VLMo	overall	81.3	—	Unverified
6	SimVLM	overall	80.34	—	Unverified
7	X2-VLM (base)	overall	80.2	—	Unverified
8	VAST	overall	80.19	—	Unverified
9	VALOR	overall	78.62	—	Unverified
10	Prompt Tuning	overall	78.53	—	Unverified