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 801–850 of 2167 papers

TitleStatusHype
HAUR: Human Annotation Understanding and Recognition Through Text-Heavy Images—0
LININ: Logic Integrated Neural Inference Network for Explanatory Visual Question AnsweringCode0
Multi-Agents Based on Large Language Models for Knowledge-based Visual Question Answering—0
TextMatch: Enhancing Image-Text Consistency Through Multimodal Optimization—0
Cross-Lingual Text-Rich Visual Comprehension: An Information Theory PerspectiveCode0
Prompting Large Language Models with Rationale Heuristics for Knowledge-based Visual Question Answering—0
Application of Multimodal Large Language Models in Autonomous Driving—0
InstructOCR: Instruction Boosting Scene Text SpottingCode0
NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional GeneralizationCode0
Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage—0
Multimodal Hypothetical Summary for Retrieval-based Multi-image Question AnsweringCode0
OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization—0
What makes a good metric? Evaluating automatic metrics for text-to-image consistency—0
Optimizing Vision-Language Interactions Through Decoder-Only Models—0
Selective State Space Memory for Large Vision-Language Models—0
VLR-Bench: Multilingual Benchmark Dataset for Vision-Language Retrieval Augmented Generation—0
Illusory VQA: Benchmarking and Enhancing Multimodal Models on Visual IllusionsCode0
Can We Generate Visual Programs Without Prompting LLMs?—0
Verb Mirage: Unveiling and Assessing Verb Concept Hallucinations in Multimodal Large Language Models—0
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling—0
T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts—0
AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?—0
Copy-Move Forgery Detection and Question Answering for Remote Sensing ImageCode0
WSI-LLaVA: A Multimodal Large Language Model for Whole Slide Image—0
CEGI: Measuring the trade-off between efficiency and carbon emissions for SLMs and VLMs—0
DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and TrustworthinessCode0
Perception Test 2024: Challenge Summary and a Novel Hour-Long VideoQA Benchmark—0
SURE-VQA: Systematic Understanding of Robustness Evaluation in Medical VQA TasksCode0
Sparse Attention Vectors: Generative Multimodal Model Features Are Discriminative Vision-Language Classifiers—0
ElectroVizQA: How well do Multi-modal LLMs perform in Electronics Visual Question Answering?—0
Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey—0
Task Progressive Curriculum Learning for Robust Visual Question Answering—0
Video-Text Dataset Construction from Multi-AI Feedback: Promoting Weak-to-Strong Preference Learning for Video Large Language Models—0
GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis—0
Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ DocumentsCode0
ReWind: Understanding Long Videos with Instructed Learnable Memory—0
Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy—0
Benchmarking Multimodal Models for Ukrainian Language Understanding Across Academic and Cultural Domains—0
mR^2AG: Multimodal Retrieval-Reflection-Augmented Generation for Knowledge-Based VQA—0
Visual Contexts Clarify Ambiguous Expressions: A Benchmark DatasetCode0
Uni-Mlip: Unified Self-supervision for Medical Vision Language Pre-training—0
Hints of Prompt: Enhancing Visual Representation for Multimodal LLMs in Autonomous Driving—0
Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios—0
LaVida Drive: Vision-Text Interaction VLM for Autonomous Driving with Token Selection, Recovery and Enhancement—0
Med-2E3: A 2D-Enhanced 3D Medical Multimodal Large Language Model—0
Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media ContextsCode0
Memory-Augmented Multimodal LLMs for Surgical VQA via Self-Contained Inquiry—0
Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question AnsweringCode0
F^3OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics—0
A Comprehensive Survey on Visual Question Answering Datasets and Algorithms—0
Show:102550
← PrevPage 17 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