HyperAI超神经

首页资讯最新论文教程数据集百科 SOTA LLM 模型天梯 GPU 天梯顶会

中文

HyperAI超神经

Visual Question Answering On Coco Visual 4

评估指标

Percentage correct

评测结果

各个模型在此基准测试上的表现结果

模型名称	Percentage correct	Paper Title	Repository
LSTM Q+I	58.2	VQA: Visual Question Answering
joint-loss	63.2	Training Recurrent Answering Units with Joint Loss Minimization for VQA	-
RelAtt	65.69	R-VQA: Learning Visual Relation Facts with Semantic Attention for Visual Question Answering
Dual-MFA	66.09	Co-attending Free-form Regions and Detections with Multi-modal Multiplicative Feature Embedding for Visual Question Answering
iBOWIMG baseline	55.9	Simple Baseline for Visual Question Answering
CNN-RNN	59.5	Image Captioning and Visual Question Answering Based on Attributes and External Knowledge	-
MRN + global features	61.8	Multimodal Residual Learning for Visual QA
FDA	59.5	A Focused Dynamic Attention Model for Visual Question Answering	-
HQI+ResNet	62.1	Hierarchical Question-Image Co-Attention for Visual Question Answering
SMem-VQA	58.2	Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering
MCB 7 att.	66.5	Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
DMN+ [xiong2016dynamic]	60.4	Dynamic Memory Networks for Visual and Textual Question Answering
QGHC+Att+Concat	65.90	Question-Guided Hybrid Convolution for Visual Question Answering	-
SAN	58.9	Stacked Attention Networks for Image Question Answering

0 of 14 row(s) selected.