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 2001–2025 of 2167 papers

Title	Date	Tasks	Status	Hype
Multimodal Explanations: Justifying Decisions and Pointing to the Evidence	Feb 15, 2018	Activity RecognitionExplainable Models	CodeCode Available	0
Generating Triples with Adversarial Networks for Scene Graph Construction	Feb 7, 2018	Attributegraph construction	—Unverified	0
Dual Recurrent Attention Units for Visual Question Answering	Feb 1, 2018	Question AnsweringVisual Question Answering	CodeCode Available	0
Object-based reasoning in VQA	Jan 29, 2018	Objectobject-detection	—Unverified	0
Game of Sketches: Deep Recurrent Models of Pictionary-style Word Guessing	Jan 29, 2018	Question AnsweringVisual Question Answering	CodeCode Available	0
Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions	Jan 27, 2018	AttributeImage Captioning	—Unverified	0
Structured Triplet Learning with POS-tag Guided Attention for Visual Question Answering	Jan 24, 2018	Multiple-choicePOS	CodeCode Available	0
DVQA: Understanding Data Visualizations via Question Answering	Jan 24, 2018	ArticlesChart Question Answering	CodeCode Available	0
Not-So-CLEVR: Visual Relations Strain Feedforward Neural Networks	Jan 1, 2018	MemorizationQuestion Answering	—Unverified	0
Interpretable Counting for Visual Question Answering	Dec 23, 2017	Question AnsweringVisual Question Answering	—Unverified	0
Visual Explanations from Hadamard Product in Multimodal Deep Networks	Dec 18, 2017	Question AnsweringVisual Question Answering	—Unverified	0
AI2-THOR: An Interactive 3D Environment for Visual AI	Dec 14, 2017	Deep Reinforcement LearningImitation Learning	CodeCode Available	1
IQA: Visual Question Answering in Interactive Environments	Dec 9, 2017	NavigateReinforcement Learning	CodeCode Available	0
Learning by Asking Questions	Dec 4, 2017	Question AnsweringVisual Question Answering	—Unverified	0
Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks	Dec 3, 2017	Question AnsweringVisual Question Answering	—Unverified	0
Multimodal Learning and Reasoning for Visual Question Answering	Dec 1, 2017	Question AnsweringRepresentation Learning	—Unverified	0
Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering	Dec 1, 2017	Question AnsweringVisual Question Answering	CodeCode Available	0
Hyper-dimensional computing for a visual question-answering system that is trainable end-to-end	Nov 28, 2017	Question AnsweringVisual Question Answering	—Unverified	0
Locally Smoothed Neural Networks	Nov 22, 2017	Face VerificationQuestion Answering	CodeCode Available	0
Visual Question Answering as a Meta Learning Task	Nov 22, 2017	Meta-LearningQuestion Answering	—Unverified	0
Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning	Nov 21, 2017	Question AnsweringReinforcement Learning	—Unverified	0
Adversarial Attacks Beyond the Image Space	Nov 20, 2017	Question AnsweringVisual Question Answering	—Unverified	0
Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments	Nov 20, 2017	Reinforcement LearningTranslation	CodeCode Available	1
Co-attending Regions and Detections with Multi-modal Multiplicative Embedding for VQA	Nov 18, 2017	FormQuestion Answering	CodeCode Available	0
Co-attending Free-form Regions and Detections with Multi-modal Multiplicative Feature Embedding for Visual Question Answering	Nov 18, 2017	FormVisual Question Answering	CodeCode Available	0

Show:10 25 50

← PrevPage 81 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