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 676–700 of 2167 papers

Title	Date	Tasks	Status	Hype
Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training	Jan 4, 2024	DescriptiveImage Captioning	CodeCode Available	1
Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles	Jan 1, 2024	Question AnsweringVisual Question Answering	—Unverified	0
Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action	Jan 1, 2024	Image GenerationInstruction Following	—Unverified	0
Synthesize Step-by-Step: Tools Templates and LLMs as Data Generators for Reasoning-Based Chart VQA	Jan 1, 2024	Chart Question AnsweringData Augmentation	—Unverified	0
DIEM: Decomposition-Integration Enhancing Multimodal Insights	Jan 1, 2024	MM-VetQuestion Answering	—Unverified	0
Mask4Align: Aligned Entity Prompting with Color Masks for Multi-Entity Localization Problems	Jan 1, 2024	Question AnsweringVisual Question Answering	—Unverified	0
Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels	Dec 28, 2023	Aesthetics Quality AssessmentImage Quality Assessment	CodeCode Available	2
Multi-Prompts Learning with Cross-Modal Alignment for Attribute-based Person Re-Identification	Dec 28, 2023	Attributecross-modal alignment	—Unverified	0
TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones	Dec 28, 2023	Computational EfficiencyImage Captioning	CodeCode Available	3
Gemini Pro Defeated by GPT-4V: Evidence from Education	Dec 27, 2023	image-classificationImage Classification	—Unverified	0
Knowledge Guided Semi-Supervised Learning for Quality Assessment of User Generated Videos	Dec 24, 2023	Representation LearningTransfer Learning	CodeCode Available	0
Q-Boost: On Visual Quality Assessment Ability of Low-level Multi-Modality Foundation Models	Dec 23, 2023	Image Quality AssessmentVideo Quality Assessment	—Unverified	0
Towards a Unified Multimodal Reasoning Framework	Dec 22, 2023	Multimodal ReasoningMultiple-choice	CodeCode Available	0
DriveLM: Driving with Graph Visual Question Answering	Dec 21, 2023	Autonomous DrivingQuestion Answering	CodeCode Available	3
LLM4VG: Large Language Models Evaluation for Video Grounding	Dec 21, 2023	Image CaptioningVideo Grounding	—Unverified	0
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks	Dec 21, 2023	Image RetrievalImage-to-Text Retrieval	CodeCode Available	1
Reducing Hallucinations: Enhancing VQA for Flood Disaster Damage Assessment with Visual Contexts	Dec 21, 2023	HallucinationQuestion Answering	—Unverified	0
Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQA	Dec 21, 2023	Contrastive Learningcounterfactual	CodeCode Available	1
Object Attribute Matters in Visual Question Answering	Dec 20, 2023	AttributeGraph Neural Network	CodeCode Available	0
Interactive Visual Task Learning for Robots	Dec 20, 2023	Continual LearningNovel Concepts	—Unverified	0
Multi-Clue Reasoning with Memory Augmentation for Knowledge-based Visual Question Answering	Dec 20, 2023	Question AnsweringVisual Question Answering	—Unverified	0
BloomVQA: Assessing Hierarchical Multi-modal Comprehension	Dec 20, 2023	Data AugmentationMemorization	—Unverified	0
Full-reference Video Quality Assessment for User Generated Content Transcoding	Dec 19, 2023	Video Quality AssessmentVisual Question Answering (VQA)	—Unverified	0
VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering	Dec 19, 2023	Image RetrievalQuestion Answering	CodeCode Available	0
EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering	Dec 19, 2023	ObjectObject Counting	CodeCode Available	1

Show:10 25 50

← PrevPage 28 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