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 101–150 of 2167 papers

TitleStatusHype
SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models—0
Localizing Before Answering: A Hallucination Evaluation Benchmark for Grounded Medical Multimodal LLMs—0
VideoMultiAgents: A Multi-Agent Framework for Video Question AnsweringCode1
An Empirical Study on Prompt Compression for Large Language ModelsCode3
Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Prediction—0
A Comprehensive Survey of Knowledge-Based Vision Question Answering Systems: The Lifecycle of Knowledge in Visual Reasoning Task—0
NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and ResultsCode1
Instruction-augmented Multimodal Alignment for Image-Text and Element Matching—0
Bridging the Semantic Gaps: Improving Medical VQA Consistency with LLM-Augmented Question Sets—0
DVLTA-VQA: Decoupled Vision-Language Modeling with Text-Guided Adaptation for Blind Video Quality Assessment—0
PuzzleBench: A Fully Dynamic Evaluation Framework for Large Multimodal Models on Puzzle Solving—0
QAVA: Query-Agnostic Visual Attack to Large Vision-Language ModelsCode0
Building Trustworthy Multimodal AI: A Review of Fairness, Transparency, and Ethics in Vision-Language Tasks—0
MMKB-RAG: A Multi-Modal Knowledge-Based Retrieval-Augmented Generation Framework—0
FVQ: A Large-Scale Dataset and A LMM-based Method for Face Video Quality AssessmentCode0
PathVLM-R1: A Reinforcement Learning-Driven Reasoning Model for Pathology Visual-Language Tasks—0
NoTeS-Bank: Benchmarking Neural Transcription and Search for Scientific Notes Understanding—0
Mimic In-Context Learning for Multimodal TasksCode1
TokenFocus-VQA: Enhancing Text-to-Image Alignment with Position-Aware Focus and Multi-Perspective Aggregations on LVLMs—0
UniRVQA: A Unified Framework for Retrieval-Augmented Vision Question Answering via Self-Reflective Joint Training—0
Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion—0
QIRL: Boosting Visual Question Answering via Optimized Question-Image Relation Learning—0
STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security InspectionCode1
SocialGesture: Delving into Multi-person Gesture Understanding—0
Reasoning LLMs for User-Aware Multimodal Conversational Agents—0
MPDrive: Improving Spatial Understanding with Marker-Based Prompt Learning for Autonomous Driving—0
KOFFVQA: An Objectively Evaluated Free-form VQA Benchmark for Large Vision-Language Models in the Korean LanguageCode0
How Well Can Vison-Language Models Understand Humans' Intention? An Open-ended Theory of Mind Question Evaluation Benchmark—0
FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMsCode1
Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields—0
Vision-Amplified Semantic Entropy for Hallucination Detection in Medical Visual Question Answering—0
VGAT: A Cancer Survival Analysis Framework Transitioning from Generative Visual Question Answering to Genomic ReconstructionCode0
LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?—0
ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation—0
Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image AnalysisCode2
Where is this coming from? Making groundedness count in the evaluation of Document VQA models—0
MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering—0
DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels—0
AMD-Hummingbird: Towards an Efficient Text-to-Video ModelCode1
Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models—0
Progressive Prompt Detailing for Improved Alignment in Text-to-Image Generative ModelsCode0
A Vision Centric Remote Sensing Benchmark—0
UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation—0
TruthLens:A Training-Free Paradigm for DeepFake Detection—0
ChatBEV: A Visual Language Model that Understands BEV Maps—0
Marten: Visual Question Answering with Mask Generation for Multi-modal Document UnderstandingCode0
NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language ModelsCode1
MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific ResearchCode1
GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing—0
DynRsl-VLM: Enhancing Autonomous Driving Perception with Dynamic Resolution Vision-Language Models—0
Show:102550
← PrevPage 3 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
9InternVL-CAccuracy81.2—Unverified
10LyricsAccuracy81.2—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