OpenCodePapers

visual-question-answering-on-coco-visual-1

Visual Question Answering (VQA)
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodePercentage correctModelNameReleaseDate
Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding✓ Link70.1MCB 7 att.2016-06-06
Co-attending Free-form Regions and Detections with Multi-modal Multiplicative Feature Embedding for Visual Question Answering✓ Link70.04Dual-MFA2017-11-18
R-VQA: Learning Visual Relation Facts with Semantic Attention for Visual Question Answering✓ Link69.60RelAtt2018-05-24
High-Order Attention Models for Visual Question Answering✓ Link69.33-Modalities: Unary + Pairwise + Ternary (ResNet)2017-11-12
Training Recurrent Answering Units with Joint Loss Minimization for VQA67.3joint-loss2016-06-12
Multimodal Residual Learning for Visual QA✓ Link66.3MRN2016-06-05
Hierarchical Question-Image Co-Attention for Visual Question Answering✓ Link66.1HQI+ResNet2016-05-31
A Focused Dynamic Attention Model for Visual Question Answering64.2FDA2016-04-06
VQA: Visual Question Answering✓ Link63.1LSTM Q+I2015-05-03
Simple Baseline for Visual Question Answering✓ Link62.0iBOWIMG baseline2015-12-07
Check out how to contribute new results. Then edit this file.