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

Showing 19011950 of 2167 papers

TitleStatusHype
Relation-Aware Graph Attention Network for Visual Question AnsweringCode0
Visual Query Answering by Entity-Attribute Graph Matching and Reasoning0
RAVEN: A Dataset for Relational and Analogical Visual rEasoNing0
Answer Them All! Toward Universal Visual Question Answering ModelsCode0
MUREL: Multimodal Relational Reasoning for Visual Question AnsweringCode0
Dual Attention Networks for Visual Reference Resolution in Visual DialogCode0
Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering0
Cycle-Consistency for Robust Visual Question Answering0
Generating Natural Language Explanations for Visual Question Answering using Scene Graphs and Visual Attention0
Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded0
VrR-VG: Refocusing Visually-Relevant Relationships0
BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship DetectionCode0
Visual Entailment: A Novel Task for Fine-Grained Image Understanding0
CLEVR-Ref+: Diagnosing Visual Reasoning with Referring ExpressionsCode0
The meaning of "most" for visual question answering models0
Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering0
Focal Visual-Text Attention for Memex Question AnsweringCode0
Dynamic Fusion with Intra- and Inter- Modality Attention Flow for Visual Question Answering0
Learning Representations of Sets through Optimized PermutationsCode0
Spatial Knowledge Distillation to aid Visual Reasoning0
Recursive Visual Attention in Visual DialogCode0
Explainable and Explicit Visual Reasoning over Scene GraphsCode0
Multi-task Learning of Hierarchical Vision-Language Representation0
Learning to Specialize with Knowledge Distillation for Visual Question Answering0
Chain of Reasoning for Visual Question Answering0
Systematic Generalization: What Is Required and Can It Be Learned?Code0
From Known to the Unknown: Transferring Knowledge to Answer Questions about Novel Visual and Semantic Concepts0
Visual Question Answering as Reading Comprehension0
Visual Entailment Task for Visually-Grounded Language Learning0
CLEAR: A Dataset for Compositional Language and Elementary Acoustic ReasoningCode0
VQA with no questions-answers trainingCode0
A dataset of clinically generated visual questions and answers about radiology images0
Explicit Bias Discovery in Visual Question Answering Models0
Zero-Shot Transfer VQA Dataset0
Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering0
Compositional Attention Networks for Interpretability in Natural Language Question Answering0
Do Explanations make VQA Models more Predictable to a Human?0
TallyQA: Answering Complex Counting QuestionsCode0
Knowing Where to Look? Analysis on Attention of Visual Question Answering System0
Overcoming Language Priors in Visual Question Answering with Adversarial Regularization0
Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language UnderstandingCode0
Transfer Learning via Unsupervised Task Discovery for Visual Question AnsweringCode0
Multimodal Differential Network for Visual Question Generation0
Convolutional Neural Networks for Video Quality Assessment0
Textually Enriched Neural Module Networks for Visual Question Answering0
The Wisdom of MaSSeS: Majority, Subjectivity, and Semantic Similarity in the Evaluation of VQA0
Cascaded Mutual Modulation for Visual ReasoningCode0
Visual Coreference Resolution in Visual Dialog using Neural Module NetworksCode0
Interpretable Visual Question Answering by Reasoning on Dependency Trees0
Straight to the Facts: Learning Knowledge Base Retrieval for Factual Visual Question Answering0
Show:102550
← PrevPage 39 of 44Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1humanAccuracy89.3Unverified
2DREAM+Unicoder-VL (MSRA)Accuracy76.04Unverified
3TRRNet (Ensemble)Accuracy74.03Unverified
4MIL-nbgaoAccuracy73.81Unverified
5Kakao BrainAccuracy73.33Unverified
6Coarse-to-Fine Reasoning, Single ModelAccuracy72.14Unverified
7270Accuracy70.23Unverified
8NSM ensemble (updated)Accuracy67.55Unverified
9VinVL-DPTAccuracy64.92Unverified
10VinVL+LAccuracy64.85Unverified
#ModelMetricClaimedVerifiedStatus
1PaLIAccuracy84.3Unverified
2BEiT-3Accuracy84.19Unverified
3VLMoAccuracy82.78Unverified
4ONE-PEACEAccuracy82.6Unverified
5mPLUG (Huge)Accuracy82.43Unverified
6CuMo-7BAccuracy82.2Unverified
7X2-VLM (large)Accuracy81.9Unverified
8MMUAccuracy81.26Unverified
9LyricsAccuracy81.2Unverified
10InternVL-CAccuracy81.2Unverified
#ModelMetricClaimedVerifiedStatus
1BEiT-3overall84.03Unverified
2mPLUG-Hugeoverall83.62Unverified
3ONE-PEACEoverall82.52Unverified
4X2-VLM (large)overall81.8Unverified
5VLMooverall81.3Unverified
6SimVLMoverall80.34Unverified
7X2-VLM (base)overall80.2Unverified
8VASToverall80.19Unverified
9VALORoverall78.62Unverified
10Prompt Tuningoverall78.53Unverified