Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit 97b5592

Browse files
committed
update
1 parent 08a2c0f commit 97b5592

3 files changed

Lines changed: 33 additions & 33 deletions

File tree

11.5 MB
Binary file not shown.

‎_papers/QA-视觉问答-A-综述.md‎

Lines changed: 33 additions & 33 deletions
Original file line numberDiff line numberDiff line change
@@ -10,39 +10,39 @@ Index
1010
<!-- TOC -->
1111

1212
- [VQA 简述](#vqa-简述)
13-
- [VQA 与其他图像任务](#vqa-与其他图像任务)
14-
- [基于对象检测的任务](#基于对象检测的任务)
15-
- [图像描述任务](#图像描述任务)
16-
- [DenseCap](#densecap)
17-
- [VQA 中的数据集](#vqa-中的数据集)
18-
- [DAQUAR](#daquar)
19-
- [COCO-QA](#coco-qa)
20-
- [VQA Dataset](#vqa-dataset)
21-
- [FM-IQA](#fm-iqa)
22-
- [Visual Genome](#visual-genome)
23-
- [Visual7W](#visual7w)
24-
- [SHAPES](#shapes)
25-
- [VQA 的评价方法 TODO](#vqa-的评价方法-todo)
13+
- [VQA 与其他图像任务](#vqa-与其他图像任务)
14+
- [基于对象检测的任务](#基于对象检测的任务)
15+
- [图像描述任务](#图像描述任务)
16+
- [DenseCap](#densecap)
17+
- [VQA 中的数据集](#vqa-中的数据集)
18+
- [DAQUAR](#daquar)
19+
- [COCO-QA](#coco-qa)
20+
- [VQA Dataset](#vqa-dataset)
21+
- [FM-IQA](#fm-iqa)
22+
- [Visual Genome](#visual-genome)
23+
- [Visual7W](#visual7w)
24+
- [SHAPES](#shapes)
25+
- [VQA 的评价方法 TODO](#vqa-的评价方法-todo)
2626
- [主流模型与方法](#主流模型与方法)
27-
- [基线模型](#基线模型)
28-
- [分类模型](#分类模型)
29-
- [生成模型](#生成模型)
30-
- [贝叶斯模型](#贝叶斯模型)
31-
- [基于 Attention 的模型](#基于-attention-的模型)
32-
- [基于 Edge Boxes 的方法](#基于-edge-boxes-的方法)
33-
- [基于 Uniform Grid 的方法](#基于-uniform-grid-的方法)
34-
- [[49] Stacked Attention Networks for Image Question Answering(SAN)](#49-stacked-attention-networks-for-image-question-answeringsan)
35-
- [[48] Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering](#48-ask-attend-and-answer-exploring-question-guided-spatial-attention-for-visual-question-answering)
36-
- [[52] Dynamic memory networks for visual and textual question answering](#52-dynamic-memory-networks-for-visual-and-textual-question-answering)
37-
- [[54] Hierarchical Question-Image Co-Attention for Visual Question Answering](#54-hierarchical-question-image-co-attention-for-visual-question-answering)
38-
- [[56] Dual attention networks for multimodal reasoning and matching](#56-dual-attention-networks-for-multimodal-reasoning-and-matching)
39-
- [基于双线性池化的模型](#基于双线性池化的模型)
40-
- [[46] Multimodal compact bilinear pooling for visual question answering and visual grounding](#46-multimodal-compact-bilinear-pooling-for-visual-question-answering-and-visual-grounding)
41-
- [[57] Hadamard Product for Low-rank Bilinear Pooling](#57-hadamard-product-for-low-rank-bilinear-pooling)
42-
- [组合模型](#组合模型)
43-
- [[44] Deep Compositional Question Answering with Neural Module Networks](#44-deep-compositional-question-answering-with-neural-module-networks)
44-
- [[55] Training recurrent answering units with joint loss minimization for VQA](#55-training-recurrent-answering-units-with-joint-loss-minimization-for-vqa)
45-
- [其他模型 TODO](#其他模型-todo)
27+
- [基线模型](#基线模型)
28+
- [分类模型](#分类模型)
29+
- [生成模型](#生成模型)
30+
- [贝叶斯模型](#贝叶斯模型)
31+
- [基于 Attention 的模型](#基于-attention-的模型)
32+
- [基于 Edge Boxes 的方法](#基于-edge-boxes-的方法)
33+
- [基于 Uniform Grid 的方法](#基于-uniform-grid-的方法)
34+
- [[49] Stacked Attention Networks for Image Question Answering(SAN)](#49-stacked-attention-networks-for-image-question-answeringsan)
35+
- [[48] Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering](#48-ask-attend-and-answer-exploring-question-guided-spatial-attention-for-visual-question-answering)
36+
- [[52] Dynamic memory networks for visual and textual question answering](#52-dynamic-memory-networks-for-visual-and-textual-question-answering)
37+
- [[54] Hierarchical Question-Image Co-Attention for Visual Question Answering](#54-hierarchical-question-image-co-attention-for-visual-question-answering)
38+
- [[56] Dual attention networks for multimodal reasoning and matching](#56-dual-attention-networks-for-multimodal-reasoning-and-matching)
39+
- [基于双线性池化的模型](#基于双线性池化的模型)
40+
- [[46] Multimodal compact bilinear pooling for visual question answering and visual grounding](#46-multimodal-compact-bilinear-pooling-for-visual-question-answering-and-visual-grounding)
41+
- [[57] Hadamard Product for Low-rank Bilinear Pooling](#57-hadamard-product-for-low-rank-bilinear-pooling)
42+
- [组合模型](#组合模型)
43+
- [[44] Deep Compositional Question Answering with Neural Module Networks](#44-deep-compositional-question-answering-with-neural-module-networks)
44+
- [[55] Training recurrent answering units with joint loss minimization for VQA](#55-training-recurrent-answering-units-with-joint-loss-minimization-for-vqa)
45+
- [其他模型 TODO](#其他模型-todo)
4646
- [参考文献](#参考文献)
4747

4848
<!-- /TOC -->
@@ -363,7 +363,7 @@ Index
363363
> 这个过程实际上跟**卷积**本身很像。
364364
<div align="center"><img src="../_assets/TIM截图20180911153132.png" height="" /></div>
365365
366-
**Attention 的作用**
366+
<!--**Attention 的作用**-->
367367

368368
### 基于 Edge Boxes 的方法
369369
> [63, 51]

‎_papers/pdf/[2018].BERT.pdf‎

578 KB
Binary file not shown.

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /