SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1301–1350 of 2167 papers

TitleStatusHype
Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?—0
LaTr: Layout-Aware Transformer for Scene-Text VQACode1
Comprehensive Visual Question Answering on Point Clouds through Compositional Scene ManipulationCode1
ScanQA: 3D Question Answering for Spatial Scene UnderstandingCode1
General Greedy De-bias LearningCode0
Task-Oriented Multi-User Semantic Communications—0
Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey—0
Understanding Attention for Vision-and-Language Tasks—0
Align and Prompt: Video-and-Language Pre-training with Entity PromptsCode1
KAT: A Knowledge Augmented Transformer for Vision-and-LanguageCode1
Distilled Dual-Encoder Model for Vision-Language UnderstandingCode1
3D Question Answering—0
Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question AnsweringCode1
Dual-Key Multimodal Backdoors for Visual Question AnsweringCode1
Improving and Diagnosing Knowledge-Based Visual Question Answering via Entity Enhanced Knowledge Injection—0
Video as Conditional Graph Hierarchy for Multi-Granular Question AnsweringCode1
Change Detection Meets Visual Question AnsweringCode1
Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation—0
MLP Architectures for Vision-and-Language Modeling: An Empirical StudyCode1
MoCA: Incorporating Multi-stage Domain Pretraining and Cross-guided Multimodal Attention for Textbook Question Answering—0
eaVQA: An Experimental Analysis on Visual Question Answering Models—0
Curriculum Learning Effectively Improves Low Data VQA—0
Debiased Visual Question Answering from Feature and Sample PerspectivesCode1
Scallop: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning—0
Robust Visual Reasoning via Language Guided Neural Module Networks—0
OCR-free Document Understanding TransformerCode3
Searching the Search Space of Vision TransformerCode1
Classification-Regression for Chart ComprehensionCode1
LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video Question Answering—0
Scene Graph Generation with Geometric Context—0
UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language ModelingCode1
Many Heads but One Brain: Fusion Brain -- a Competition and a Single Multimodal Multitask ArchitectureCode1
Florence: A New Foundation Model for Computer VisionCode1
A Confidence-Based Interface for Neuro-Symbolic Visual Question Answering—0
Medical Visual Question Answering: A Survey—0
UFO: A UniFied TransfOrmer for Vision-Language Representation Learning—0
Blind VQA on 360° Video via Progressively Learning from Pixels, Frames and VideoCode0
Achieving Human Parity on Visual Question Answering—0
Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation—0
Co-VQA : Answering by Interactive Sub Question Sequence—0
Uncertainty-based Visual Question Answering: Estimating Semantic Inconsistency between Image and Knowledge Base—0
A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models—0
Question-Led Semantic Structure Enhanced Attentions for VQA—0
ViQuAE, a Dataset for Knowledge-based Visual Question Answering about Named EntitiesCode0
Breaking Down Questions for Outside-Knowledge Visual Question Answering—0
Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual ConceptsCode1
Language bias in Visual Question Answering: A Survey and Taxonomy—0
Document AI: Benchmarks, Models and Applications—0
No-Reference Video Quality Assessment Based on Benford’s Law and Perceptual FeaturesCode0
Graph Relation Transformer: Incorporating pairwise object features into the Transformer architecture—0
Show:102550
← PrevPage 27 of 44Next →
All datasetsGQA Test2019VQA v2 test-devVQA v2 test-stdOK-VQAMSVD-QADocVQA testMSRVTT-QAInfographicVQAGQA test-devVizWiz 2020 VQAA-OKVQACLEVR

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1humanAccuracy89.3—Unverified
2DREAM+Unicoder-VL (MSRA)Accuracy76.04—Unverified
3TRRNet (Ensemble)Accuracy74.03—Unverified
4MIL-nbgaoAccuracy73.81—Unverified
5Kakao BrainAccuracy73.33—Unverified
6Coarse-to-Fine Reasoning, Single ModelAccuracy72.14—Unverified
7270Accuracy70.23—Unverified
8NSM ensemble (updated)Accuracy67.55—Unverified
9VinVL-DPTAccuracy64.92—Unverified
10VinVL+LAccuracy64.85—Unverified
#ModelMetricClaimedVerifiedStatus
1PaLIAccuracy84.3—Unverified
2BEiT-3Accuracy84.19—Unverified
3VLMoAccuracy82.78—Unverified
4ONE-PEACEAccuracy82.6—Unverified
5mPLUG (Huge)Accuracy82.43—Unverified
6CuMo-7BAccuracy82.2—Unverified
7X2-VLM (large)Accuracy81.9—Unverified
8MMUAccuracy81.26—Unverified
9LyricsAccuracy81.2—Unverified
10InternVL-CAccuracy81.2—Unverified
#ModelMetricClaimedVerifiedStatus
1BEiT-3overall84.03—Unverified
2mPLUG-Hugeoverall83.62—Unverified
3ONE-PEACEoverall82.52—Unverified
4X2-VLM (large)overall81.8—Unverified
5VLMooverall81.3—Unverified
6SimVLMoverall80.34—Unverified
7X2-VLM (base)overall80.2—Unverified
8VASToverall80.19—Unverified
9VALORoverall78.62—Unverified
10Prompt Tuningoverall78.53—Unverified