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 20512100 of 2167 papers

TitleStatusHype
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question AnsweringCode1
Improved Bilinear Pooling with CNNs0
Video Question Answering via Attribute-Augmented Attention Network Learning0
Visual Question Answering with Memory-Augmented Networks0
Effective Approaches to Batch Parallelization for Dynamic Neural Network ArchitecturesCode0
Modulating early visual processing by languageCode0
Multi-Level Attention Networks for Visual Question Answering0
Are You Smarter Than a Sixth Grader? Textbook Question Answering for Multimodal Machine Comprehension0
Kernel Pooling for Convolutional Neural Networks0
Knowledge Acquisition for Visual Question Answering via Iterative Querying0
Segmentation Guided Attention Networks for Visual Question Answering0
Multimodal Machine Learning: Integrating Language, Vision and Speech0
A Corpus of Natural Language for Visual Reasoning0
Compact Tensor Pooling for Visual Question Answering0
A simple neural network module for relational reasoningCode0
Deep learning evaluation using deep linguistic processing0
MUTAN: Multimodal Tucker Fusion for Visual Question AnsweringCode0
ParlAI: A Dialog Research Software PlatformCode1
Learning Convolutional Text Representations for Visual Question AnsweringCode0
Survey of Visual Question Answering: Datasets and Techniques0
Inferring and Executing Programs for Visual ReasoningCode0
The Forgettable-Watcher Model for Video Question Answering0
The Promise of Premise: Harnessing Question Premises in Visual Question AnsweringCode0
Speech-Based Visual Question AnsweringCode0
C-VQA: A Compositional Split of the Visual Question Answering (VQA) v1.0 Dataset0
Being Negative but Constructively: Lessons Learnt from Creating Better Visual Question Answering Datasets0
Learning to Reason: End-to-End Module Networks for Visual Question AnsweringCode0
ShapeWorld - A new test methodology for multimodal language understandingCode0
TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question AnsweringCode0
What's in a Question: Using Visual Questions as a Form of SupervisionCode0
Show, Ask, Attend, and Answer: A Strong Baseline For Visual Question AnsweringCode0
An Empirical Evaluation of Visual Question Answering for Novel Objects0
It Takes Two to Tango: Towards Theory of AI's Mind0
Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks0
An Analysis of Visual Question Answering Algorithms0
Recurrent and Contextual Models for Visual Question Answering0
Multimodal Compact Bilinear Pooling for Multimodal Neural Machine Translation0
Learning Cooperative Visual Dialog Agents with Deep Reinforcement LearningCode1
VQABQ: Visual Question Answering by Basic Questions0
End-to-end optimization of goal-driven and visually grounded dialogue systemsCode0
Tree Memory Networks for Modelling Long-term Temporal Dependencies0
Task-driven Visual Saliency and Attention-based Visual Question Answering0
Vision and Language Integration: Moving beyond Objects0
CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual ReasoningCode1
The VQA-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions0
Attentive Explanations: Justifying Decisions and Pointing to the Evidence0
VIBIKNet: Visual Bidirectional Kernelized Network for Visual Question AnsweringCode0
Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question AnsweringCode0
Visual Question Answering with Question Representation Update (QRU)0
The Development of Multimodal Lexical Resources0
Show:102550
← PrevPage 42 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