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 851–875 of 2167 papers

Title	Date	Tasks	Status	Hype
Deep Equilibrium Multimodal Fusion	Jun 29, 2023	Visual Question Answering (VQA)	—Unverified	0
LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding	Jun 29, 2023	16kImage Captioning	CodeCode Available	2
Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering	Jun 29, 2023	Answer GenerationQuestion Answering	CodeCode Available	1
Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering	Jun 28, 2023	Passage RetrievalQuestion Answering	CodeCode Available	0
Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic	Jun 27, 2023	Image CaptioningReferring Expression Segmentation	CodeCode Available	2
Kosmos-2: Grounding Multimodal Large Language Models to the World	Jun 26, 2023	Image CaptioningIn-Context Learning	CodeCode Available	1
Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning	Jun 26, 2023	HallucinationVisual Question Answering	CodeCode Available	2
FunQA: Towards Surprising Video Comprehension	Jun 26, 2023	Question AnsweringText Generation	CodeCode Available	1
Visual Question Answering in Remote Sensing with Cross-Attention and Multimodal Information Bottleneck	Jun 25, 2023	object-detectionObject Detection	—Unverified	0
StarVQA+: Co-training Space-Time Attention for Video Quality Assessment	Jun 21, 2023	Video Quality AssessmentVisual Question Answering (VQA)	CodeCode Available	0
Investigating Prompting Techniques for Zero- and Few-Shot Visual Question Answering	Jun 16, 2023	Image CaptioningQuestion Answering	CodeCode Available	1
Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories	Jun 15, 2023	Question AnsweringRetrieval	—Unverified	0
COSA: Concatenated Sample Pretrained Vision-Language Foundation Model	Jun 15, 2023	Formmodel	CodeCode Available	1
Improving Selective Visual Question Answering by Learning from Your Peers	Jun 14, 2023	Question AnsweringVisual Question Answering	CodeCode Available	1
Scalable Neural-Probabilistic Answer Set Programming	Jun 14, 2023	Probabilistic ProgrammingQuestion Answering	CodeCode Available	1
Visual Question Answering (VQA) on Images with Superimposed Text	Jun 13, 2023	Question AnsweringVisual Question Answering	—Unverified	0
AVIS: Autonomous Visual Information Seeking with Large Language Model Agent	Jun 13, 2023	Decision MakingLanguage Modeling	—Unverified	0
Weakly Supervised Visual Question Answer Generation	Jun 11, 2023	Answer GenerationDependency Parsing	—Unverified	0
Modular Visual Question Answering via Code Generation	Jun 8, 2023	Code GenerationIn-Context Learning	CodeCode Available	1
Knowledge Detection by Relevant Question and Image Attributes in Visual Question Answering	Jun 8, 2023	Question AnsweringRetrieval	—Unverified	0
Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards	Jun 7, 2023	DiversityImage Captioning	CodeCode Available	1
Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!	Jun 6, 2023	counterfactualData Augmentation	CodeCode Available	1
Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes	Jun 4, 2023	Common Sense ReasoningQuestion Answering	—Unverified	0
DocFormerv2: Local Features for Document Understanding	Jun 2, 2023	Decoderdocument understanding	CodeCode Available	1
MetaVL: Transferring In-Context Learning Ability From Language Models to Vision-Language Models	Jun 2, 2023	In-Context LearningLanguage Modeling	—Unverified	0

Show:10 25 50

← PrevPage 35 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