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 351–400 of 2167 papers

TitleStatusHype
SemiHVision: Enhancing Medical Multimodal Models with a Semi-Human Annotated Dataset and Fine-Tuned Instruction GenerationCode0
ChitroJera: A Regionally Relevant Visual Question Answering Dataset for Bangla—0
LLaVA-Ultra: Large Chinese Language and Vision Assistant for Ultrasound—0
ViConsFormer: Constituting Meaningful Phrases of Scene Texts using Transformer-based Method in Vietnamese Text-based Visual Question AnsweringCode0
NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples—0
Latent Image and Video Resolution Prediction using Convolutional Neural Networks—0
RescueADI: Adaptive Disaster Interpretation in Remote Sensing Images with Autonomous Agents—0
ActionCOMET: A Zero-shot Approach to Learn Image-specific Commonsense Concepts about ActionsCode0
Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts?Code0
MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language ModelsCode3
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global CuisinesCode1
VividMed: Vision Language Model with Versatile Visual Grounding for MedicineCode1
SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding—0
Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMsCode0
Towards Foundation Models for 3D Vision: How Close Are We?Code1
Eliminating the Language Bias for Visual Question Answering with fine-grained Causal Intervention—0
LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers ContentCode1
Skipping Computations in Multimodal LLMsCode1
Declarative Knowledge Distillation from Large Language Models for Visual Question Answering DatasetsCode0
ViT3D Alignment of LLaMA3: 3D Medical Image Report Generation—0
Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunities—0
Secure Video Quality Assessment Resisting Adversarial Attacks—0
Beyond Captioning: Task-Specific Prompting for Improved VLM Performance in Mathematical Reasoning—0
ERVQA: A Dataset to Benchmark the Readiness of Large Vision Language Models in Hospital EnvironmentsCode0
DataEnvGym: Data Generation Agents in Teacher Environments with Student FeedbackCode1
ActiView: Evaluating Active Perception Ability for Multimodal Large Language ModelsCode1
MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM IntegrationCode1
TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable QuestionsCode0
BadCM: Invisible Backdoor Attack Against Cross-Modal LearningCode1
LoGra-Med: Long Context Multi-Graph Alignment for Medical Vision-Language Model—0
Video Instruction Tuning With Synthetic Data—0
Why context matters in VQA and Reasoning: Semantic interventions for VLM input modalities—0
Backdooring Vision-Language Models with Out-Of-Distribution Data—0
Unleashing the Potentials of Likelihood Composition for Multi-modal Language ModelsCode0
BabelBench: An Omni Benchmark for Code-Driven Analysis of Multimodal and Multistructured DataCode0
FMBench: Benchmarking Fairness in Multimodal Large Language Models on Medical Tasks—0
A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense ReasoningCode1
T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness RecognitionCode1
Visual Question Decomposition on Multimodal Large Language Models—0
TrojVLM: Backdoor Attack Against Vision Language Models—0
3D-CT-GPT: Generating 3D Radiology Reports through Integration of Large Vision-Language Models—0
Charting the Future: Using Chart Question-Answering for Scalable Evaluation of LLM-Driven Data Visualizations—0
DARE: Diverse Visual Question Answering with Robustness Evaluation—0
ZALM3: Zero-Shot Enhancement of Vision-Language Alignment via In-Context Information in Multi-Turn Multimodal Medical Dialogue—0
A Unified Hallucination Mitigation Framework for Large Vision-Language ModelsCode0
MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation modelsCode1
Advancing Video Quality Assessment for AIGC—0
Revisiting Video Quality Assessment from the Perspective of GeneralizationCode0
Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluation—0
Towards Efficient and Robust VQA-NLE Data Generation with Large Vision-Language ModelsCode0
Show:102550
← PrevPage 8 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