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 20012050 of 2167 papers

TitleStatusHype
Two can play this Game: Visual Dialog with Discriminative Question Generation and Answering0
Motion-Appearance Co-Memory Networks for Video Question Answering0
Generalized Hadamard-Product Fusion Operators for Visual Question Answering0
Explicit Reasoning over End-to-End Neural Architectures for Visual Question Answering0
Attention on Attention: Architectures for Visual Question Answering (VQA)Code0
VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions0
A Dataset and Architecture for Visual Reasoning with a Working MemoryCode0
Inverse Visual Question Answering: A New Benchmark and VQA Diagnosis Tool0
Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual ReasoningCode0
VizWiz Grand Challenge: Answering Visual Questions from Blind PeopleCode0
Multimodal Explanations: Justifying Decisions and Pointing to the EvidenceCode0
Learning to Count Objects in Natural Images for Visual Question AnsweringCode0
Generating Triples with Adversarial Networks for Scene Graph Construction0
Dual Recurrent Attention Units for Visual Question AnsweringCode0
Game of Sketches: Deep Recurrent Models of Pictionary-style Word GuessingCode0
Object-based reasoning in VQA0
Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions0
Structured Triplet Learning with POS-tag Guided Attention for Visual Question AnsweringCode0
DVQA: Understanding Data Visualizations via Question AnsweringCode0
Not-So-CLEVR: Visual Relations Strain Feedforward Neural Networks0
Interpretable Counting for Visual Question Answering0
Visual Explanations from Hadamard Product in Multimodal Deep Networks0
IQA: Visual Question Answering in Interactive EnvironmentsCode0
Learning by Asking Questions0
Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks0
Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question AnsweringCode0
Multimodal Learning and Reasoning for Visual Question Answering0
Hyper-dimensional computing for a visual question-answering system that is trainable end-to-end0
Visual Question Answering as a Meta Learning Task0
Locally Smoothed Neural NetworksCode0
Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning0
Adversarial Attacks Beyond the Image Space0
Co-attending Free-form Regions and Detections with Multi-modal Multiplicative Feature Embedding for Visual Question AnsweringCode0
Co-attending Regions and Detections with Multi-modal Multiplicative Embedding for VQACode0
Attentive Explanations: Justifying Decisions and Pointing to the Evidence (Extended Abstract)0
A Novel Framework for Robustness Analysis of Visual QA Models0
High-Order Attention Models for Visual Question AnsweringCode0
Active Learning for Visual Question Answering: An Empirical StudyCode0
FigureQA: An Annotated Figure Dataset for Visual ReasoningCode0
iVQA: Inverse Visual Question Answering0
Fooling Vision and Language Models Despite Localization and Attention Mechanism0
Survey of Recent Advances in Visual Question Answering0
Visual Reference Resolution using Attention Memory for Visual Dialog0
Visual Question Generation as Dual Task of Visual Question Answering0
Exploring Human-like Attention Supervision in Visual Question Answering0
Robustness Analysis of Visual QA Models by Basic Questions0
Memory Augmented Neural Networks for Natural Language Processing0
Sheffield MultiMT: Using Object Posterior Predictions for Multimodal Machine Translation0
Spatial Language Understanding with Multimodal Graphs using Declarative Learning based Programming0
Data Augmentation for Visual Question Answering0
Show:102550
← PrevPage 41 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