OpenCodePapers

visual-question-answering-on-coco-visual-4

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✓ Link66.5MCB 7 att.2016-06-06
Co-attending Free-form Regions and Detections with Multi-modal Multiplicative Feature Embedding for Visual Question Answering✓ Link66.09Dual-MFA2017-11-18
Question-Guided Hybrid Convolution for Visual Question Answering65.90QGHC+Att+Concat2018-08-08
R-VQA: Learning Visual Relation Facts with Semantic Attention for Visual Question Answering✓ Link65.69RelAtt2018-05-24
Training Recurrent Answering Units with Joint Loss Minimization for VQA63.2joint-loss2016-06-12
Hierarchical Question-Image Co-Attention for Visual Question Answering✓ Link62.1HQI+ResNet2016-05-31
Multimodal Residual Learning for Visual QA✓ Link61.8MRN + global features2016-06-05
Dynamic Memory Networks for Visual and Textual Question Answering✓ Link60.4DMN+ [xiong2016dynamic]2016-03-04
Image Captioning and Visual Question Answering Based on Attributes and External Knowledge59.5CNN-RNN2016-03-09
A Focused Dynamic Attention Model for Visual Question Answering59.5FDA2016-04-06
Stacked Attention Networks for Image Question Answering✓ Link58.9SAN2015-11-07
VQA: Visual Question Answering✓ Link58.2LSTM Q+I2015-05-03
Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering✓ Link58.2SMem-VQA2015-11-17
Simple Baseline for Visual Question Answering✓ Link55.9iBOWIMG baseline2015-12-07
Check out how to contribute new results. Then edit this file.