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 351–375 of 2167 papers

Title	Date	Tasks	Status	Hype
Hierarchical multimodal transformers for Multi-Page DocVQA	Dec 7, 2022	DecoderQuestion Answering	CodeCode Available	1
Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning	Dec 1, 2022	Domain GeneralizationQuestion Answering	CodeCode Available	1
Self-supervised vision-language pretraining for Medical visual question answering	Nov 24, 2022	Contrastive LearningImage-text matching	CodeCode Available	1
Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning	Nov 24, 2022	cross-modal alignmentImage-text Retrieval	CodeCode Available	1
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations	Nov 21, 2022	Contrastive LearningRepresentation Learning	CodeCode Available	1
I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision	Nov 17, 2022	Image CaptioningQuestion Answering	CodeCode Available	1
MapQA: A Dataset for Question Answering on Choropleth Maps	Nov 15, 2022	ArticlesQuestion Answering	CodeCode Available	1
PromptCap: Prompt-Guided Task-Aware Image Captioning	Nov 15, 2022	Image CaptioningLanguage Modelling	CodeCode Available	1
Visual Named Entity Linking: A New Dataset and A Baseline	Nov 9, 2022	Entity LinkingImage Retrieval	CodeCode Available	1
VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge	Oct 24, 2022	Question AnsweringVisual Question Answering	CodeCode Available	1
Meta-Learning via Classifier(-free) Diffusion Guidance	Oct 17, 2022	Few-Shot LearningImage Generation	CodeCode Available	1
MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting	Oct 13, 2022	Image CaptioningQuestion Answering	CodeCode Available	1
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding	Oct 12, 2022	document-image-classificationDocument Image Classification	CodeCode Available	1
SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models	Oct 12, 2022	ObjectQuestion Answering	CodeCode Available	1
MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model	Oct 11, 2022	Contrastive LearningImage-text matching	CodeCode Available	1
Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning	Oct 10, 2022	Contrastive LearningQuestion Answering	CodeCode Available	1
Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA	Oct 10, 2022	Question AnsweringVisual Question Answering	CodeCode Available	1
Linearly Mapping from Image to Text Space	Sep 30, 2022	Image CaptioningImage to text	CodeCode Available	1
TVLT: Textless Vision-Language Transformer	Sep 28, 2022	Automatic Speech Recognition (ASR)Image Retrieval	CodeCode Available	1
Towards Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline	Sep 24, 2022	Question AnsweringVisual Question Answering	CodeCode Available	1
Panoramic Vision Transformer for Saliency Detection in 360° Videos	Sep 19, 2022	Saliency DetectionSaliency Prediction	CodeCode Available	1
MaXM: Towards Multilingual Visual Question Answering	Sep 12, 2022	Question AnsweringTranslation	CodeCode Available	1
An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling	Sep 4, 2022	Fill MaskOptical Flow Estimation	CodeCode Available	1
2BiVQA: Double Bi-LSTM based Video Quality Assessment of UGC Videos	Aug 31, 2022	Video Quality AssessmentVisual Question Answering (VQA)	CodeCode Available	1
Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment	Aug 29, 2022	cross-modal alignmentImage-text Retrieval	CodeCode Available	1

Show:10 25 50

← PrevPage 15 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