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 1576–1600 of 2167 papers

Title	Date	Tasks	Status	Hype
Just Ask: Learning to Answer Questions from Millions of Narrated Videos	Dec 1, 2020	Question AnsweringQuestion Generation	CodeCode Available	1
Multimodal Graph Networks for Compositional Generalization in Visual Question Answering	Dec 1, 2020	Graph Neural NetworkQuestion Answering	—Unverified	0
Patch-VQ: 'Patching Up' the Video Quality Problem	Nov 27, 2020	Video Quality AssessmentVisual Question Answering (VQA)	CodeCode Available	1
Point and Ask: Incorporating Pointing into Visual Question Answering	Nov 27, 2020	Question AnsweringVisual Question Answering	CodeCode Available	1
Learning from Lexical Perturbations for Consistent Visual Question Answering	Nov 26, 2020	Question AnsweringVisual Question Answering	CodeCode Available	0
Transformation Driven Visual Reasoning	Nov 26, 2020	AttributeTriplet	CodeCode Available	1
Siamese Tracking with Lingual Object Constraints	Nov 23, 2020	ObjectObject Tracking	CodeCode Available	0
Large Scale Multimodal Classification Using an Ensemble of Transformer Models and Co-Attention	Nov 23, 2020	ClassificationGeneral Classification	CodeCode Available	1
Interpretable Visual Reasoning via Induced Symbolic Space	Nov 23, 2020	Visual Question Answering (VQA)Visual Reasoning	CodeCode Available	0
Modular Graph Attention Network for Complex Visual Relational Reasoning	Nov 22, 2020	Graph AttentionQuestion Answering	—Unverified	0
LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering	Nov 21, 2020	Answer GenerationQuestion Answering	CodeCode Available	1
Logically Consistent Loss for Visual Question Answering	Nov 19, 2020	Multi-Task LearningQuestion Answering	—Unverified	0
Generating Natural Questions from Images for Multimodal Assistants	Nov 17, 2020	Common Sense ReasoningNatural Questions	—Unverified	0
CapWAP: Captioning with a Purpose	Nov 9, 2020	Image CaptioningQuestion Answering	—Unverified	0
Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles	Nov 7, 2020	Natural Language InferenceQuestion Answering	CodeCode Available	0
Disentangling 3D Prototypical Networks For Few-Shot Concept Learning	Nov 6, 2020	3D geometry3D Object Detection	CodeCode Available	1
An Improved Attention for Visual Question Answering	Nov 4, 2020	DecoderQuestion Answering	CodeCode Available	0
Reasoning Over History: Context Aware Visual Dialog	Nov 2, 2020	coreference-resolutionCoreference Resolution	—Unverified	0
Can Pre-training help VQA with Lexical Variations?	Nov 1, 2020	Question AnsweringVisual Question Answering	—Unverified	0
Representation, Learning and Reasoning on Spatial Language for Downstream NLP Tasks	Nov 1, 2020	Common Sense ReasoningQuestion Answering	—Unverified	0
ConceptBert: Concept-Aware Representation for Visual Question Answering	Nov 1, 2020	Common Sense ReasoningQuestion Answering	CodeCode Available	1
ISAAQ - Mastering Textbook Questions with Pre-trained Transformers and Bottom-Up and Top-Down Attention	Nov 1, 2020	Multiple-choiceQuestion Answering	—Unverified	0
CapWAP: Image Captioning with a Purpose	Nov 1, 2020	Image CaptioningQuestion Answering	—Unverified	0
Learning to Contrast the Counterfactual Samples for Robust Visual Question Answering	Nov 1, 2020	Contrastive Learningcounterfactual	CodeCode Available	1
STL-CQA: Structure-based Transformers with Localization and Encoding for Chart Question Answering	Nov 1, 2020	Chart Question AnsweringQuestion Answering	—Unverified	0

Show:10 25 50

← PrevPage 64 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	InternVL-C	Accuracy	81.2	—	Unverified
10	Lyrics	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