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 951–975 of 2167 papers

Title	Date	Tasks	Status	Score
Enhancing Continual Learning in Visual Question Answering with Modality-Aware Feature Distillation	Jun 27, 2024	Continual LearningQuestion Answering	CodeCode Available	5
Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering	Dec 2, 2016	Visual Question AnsweringVisual Question Answering (VQA)	CodeCode Available	5
Answer Them All! Toward Universal Visual Question Answering Models	Mar 1, 2019	AllQuestion Answering	CodeCode Available	5
M^2ConceptBase: A Fine-Grained Aligned Concept-Centric Multimodal Knowledge Base	Dec 16, 2023	cross-modal alignmentKnowledge Graphs	CodeCode Available	5
Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding	Mar 18, 2025	document understandingQuestion Answering	CodeCode Available	5
End-to-end optimization of goal-driven and visually grounded dialogue systems	Mar 15, 2017	DecoderDeep Reinforcement Learning	CodeCode Available	5
End-to-End Instance Segmentation with Recurrent Attention	May 30, 2016	Autonomous DrivingImage Captioning	CodeCode Available	5
Answer Questions with Right Image Regions: A Visual Attention Regularization Approach	Feb 3, 2021	Question AnsweringVisual Grounding	CodeCode Available	5
End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features	Jun 21, 2018	Question AnsweringVideo Description	CodeCode Available	5
Adversarial Training with OCR Modality Perturbation for Scene-Text Visual Question Answering	Mar 14, 2024	Optical Character RecognitionOptical Character Recognition (OCR)	CodeCode Available	5
LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question Answering	May 29, 2021	Question AnsweringVisual Question Answering	CodeCode Available	5
Logical Implications for Visual Question Answering Consistency	Mar 16, 2023	Language ModelingLanguage Modelling	CodeCode Available	5
Locally Smoothed Neural Networks	Nov 22, 2017	Face VerificationQuestion Answering	CodeCode Available	5
ELIP: Efficient Language-Image Pre-training with Fewer Vision Tokens	Sep 28, 2023	Cross-Modal RetrievalGPU	CodeCode Available	5
Answering Questions about Data Visualizations using Efficient Bimodal Fusion	Aug 5, 2019	Chart Question AnsweringOptical Character Recognition	CodeCode Available	5
Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question Answering	Sep 13, 2021	Data AugmentationQuestion Answering	CodeCode Available	5
Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning	Jun 9, 2025	Future predictionQuestion Answering	CodeCode Available	5
LLM-Assisted Multi-Teacher Continual Learning for Visual Question Answering in Robotic Surgery	Feb 26, 2024	Continual LearningExemplar-Free	CodeCode Available	5
LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models	Aug 26, 2024	Large Language ModelVideo Quality Assessment	CodeCode Available	5
Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View	Oct 30, 2020	Face Recognitionimage-classification	CodeCode Available	5
LXMERT Model Compression for Visual Question Answering	Oct 23, 2023	modelModel Compression	CodeCode Available	5
LININ: Logic Integrated Neural Inference Network for Explanatory Visual Question Answering	Dec 24, 2024	Explanatory Visual Question AnsweringMultimodal Reasoning	CodeCode Available	5
Effective Approaches to Batch Parallelization for Dynamic Neural Network Architectures	Jul 8, 2017	Mixture-of-ExpertsQuestion Answering	CodeCode Available	5
LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking	Apr 18, 2022	cross-modal alignmentDocument AI	CodeCode Available	5
Lightweight Recurrent Cross-modal Encoder for Video Question Answering	Jun 30, 2023	Action RecognitionQuestion Answering	CodeCode Available	5

Show:10 25 50

← PrevPage 39 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