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 451–500 of 2167 papers

TitleStatusHype
Bayesian Low-Rank LeArning (Bella): A Practical Approach to Bayesian Neural NetworksCode0
Pyramid Coder: Hierarchical Code Generator for Compositional Visual Question Answering—0
Highly Efficient No-reference 4K Video Quality Assessment with Full-Pixel Covering Sampling and Training Strategy—0
Take A Step Back: Rethinking the Two Stages in Visual Reasoning—0
Multi-label Cluster Discrimination for Visual Representation LearningCode4
Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in VideosCode2
Improved Few-Shot Image Classification Through Multiple-Choice Questions—0
Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models—0
QuIIL at T3 challenge: Towards Automation in Life-Saving Intervention Procedures from First-Person ViewCode0
Visual Haystacks: A Vision-Centric Needle-In-A-Haystack BenchmarkCode1
Multimodal Reranking for Knowledge-Intensive Visual Question Answering—0
ProcTag: Process Tagging for Assessing the Efficacy of Document Instruction Data—0
EchoSight: Advancing Visual-Language Models with Wiki Knowledge—0
ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality AssessmentCode1
TM-PATHVQA:90000+ Textless Multilingual Questions for Medical Visual Question Answering—0
SPIQA: A Dataset for Multimodal Question Answering on Scientific PapersCode2
Segmentation-guided Attention for Visual Question Answering from Remote Sensing Images—0
Extracting Training Data from Document-Based VQA Models—0
VQA-Diff: Exploiting VQA and Diffusion for Zero-Shot Image-to-3D Vehicle Asset Generation in Autonomous Driving—0
Large Language Models Understand LayoutCode0
WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question AnsweringCode2
CLIPVQA:Video Quality Assessment via CLIPCode0
FlowLearn: Evaluating Large Vision-Language Models on Flowchart UnderstandingCode1
RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language ModelsCode2
Black-box Model Ensembling for Textual and Visual Question Answering via Information FusionCode0
MiniGPT-Med: Large Language Model as a General Interface for Radiology DiagnosisCode2
Visual Robustness Benchmark for Visual Question Answering (VQA)Code0
MindBench: A Comprehensive Benchmark for Mind Map Structure Recognition and Analysis—0
BACON: Improving Clarity of Image Captions via Bag-of-Concept Graphs—0
D-Rax: Domain-specific Radiologic assistant leveraging multi-modal data and eXpert model predictions—0
A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document UnderstandingCode2
Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness—0
https://arxiv.org/abs/2407.00634Code0
μ-Bench: A Vision-Language Benchmark for Microscopy UnderstandingCode0
Hierarchical Memory for Long Video QA—0
Tarsier: Recipes for Training and Evaluating Large Video Description ModelsCode4
From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data SynthesisCode1
STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-AnsweringCode1
SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs—0
Disentangling Knowledge-based and Visual Reasoning by Question Decomposition in KB-VQA—0
Enhancing Continual Learning in Visual Question Answering with Modality-Aware Feature DistillationCode0
RAVEN: Multitask Retrieval Augmented Vision-Language Learning—0
HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at ScaleCode3
On the Role of Visual Grounding in VQA—0
MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs—0
Long Context Transfer from Language to VisionCode4
Priorformer: A UGC-VQA Method with content and distortion priors—0
Losing Visual Needles in Image Haystacks: Vision Language Models are Easily Distracted in Short and Long Contexts—0
Tri-VQA: Triangular Reasoning Medical Visual Question Answering for Multi-Attribute Analysis—0
VGA: Vision GUI Assistant -- Minimizing Hallucinations through Image-Centric Fine-TuningCode0
Show:102550
← PrevPage 10 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