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
PeFoMed: Parameter Efficient Fine-tuning of Multimodal Large Language Models for Medical ImagingCode2
Oscar: Object-Semantics Aligned Pre-training for Vision-Language TasksCode2
A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document UnderstandingCode2
Retrieval Augmented Visual Question Answering with Outside KnowledgeCode2
ScreenAI: A Vision-Language Model for UI and Infographics UnderstandingCode2
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator TrajectoriesCode2
VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality AssessmentCode2
OCRBench: On the Hidden Mystery of OCR in Large Multimodal ModelsCode2
Pix2Struct: Screenshot Parsing as Pretraining for Visual Language UnderstandingCode2
NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving ScenarioCode2
NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and ResultsCode2
Towards a Multimodal Large Language Model with Pixel-Level Insight for BiomedicineCode2
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human PreferenceCode2
Neighbourhood Representative Sampling for Efficient End-to-end Video Quality AssessmentCode2
DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language ModelsCode2
VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and DatasetCode2
Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language ModelCode2
MTVQA: Benchmarking Multilingual Text-Centric Visual Question AnsweringCode2
PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical DocumentsCode2
MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference OptimizationCode2
MiniGPT-Med: Large Language Model as a General Interface for Radiology DiagnosisCode2
Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language ModelsCode2
Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image AnalysisCode2
Visual Programming: Compositional visual reasoning without trainingCode2
VQA^2: Visual Question Answering for Video Quality AssessmentCode2
When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token PruningCode2
Med-Flamingo: a Multimodal Medical Few-shot LearnerCode2
LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image UnderstandingCode2
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-ExpertsCode2
LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer LearningCode2
MedPromptX: Grounded Multimodal Prompting for Chest X-ray DiagnosisCode2
Learning to Compose Dynamic Tree Structures for Visual ContextsCode2
InstructBLIP: Towards General-purpose Vision-Language Models with Instruction TuningCode2
Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question AnsweringCode2
Grounding-IQA: Multimodal Language Grounding Model for Image Quality AssessmentCode2
HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language ModelsCode2
GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AICode2
GPT4RoI: Instruction Tuning Large Language Model on Region-of-InterestCode2
GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question AnsweringCode2
Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in VideosCode2
Frontiers in Intelligent ColonoscopyCode2
KVQ: Kwai Video Quality Assessment for Short-form VideosCode2
GIT: A Generative Image-to-text Transformer for Vision and LanguageCode2
Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question AnsweringCode2
CoLLaVO: Crayon Large Language and Vision mOdelCode2
LM4LV: A Frozen Large Language Model for Low-level Vision TasksCode2
PoseScript: Linking 3D Human Poses and Natural LanguageCode2
CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual ReasoningCode1
Comprehensive Visual Question Answering on Point Clouds through Compositional Scene ManipulationCode1
Expectation-Maximization Contrastive Learning for Compact Video-and-Language RepresentationsCode1
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
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