# Multi-label Classification
### Paper
:::info
網路上人推薦的且比較舊的
* [(2014) A Review on Multi-Label Learning Algorithms](https://ieeexplore.ieee.org/document/6471714)
* [(2015) A Tutorial on Multilabel Learning](https://dl.acm.org/doi/pdf/10.1145/2716262?download=true)
* [(2013) Transductive Multilabel Learning via Label Set Propagation](https://ieeexplore.ieee.org/document/5936063)

:::

:::success
我在IEEE和Google Scholar找的
* [(2015) Multi-label active learning for image classification](https://ieeexplore.ieee.org/document/7026058)
>將**主動學習(Active Learning)** 應用於多標籤分類。
* [(2016) CNN-RNN: A Unified Framework for Multi-Label Image Classification](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Wang_CNN-RNN_A_Unified_CVPR_2016_paper.pdf)
> 處理多標籤分類的傳統方法是為每個類別學習獨立的分類器，並對分類結果採用排名或閾值劃分。這樣會**無法利用圖片中的標籤依賴性**。

* [(2019) Multi-Label Image Recognition with Graph Convolutional Networks](https://zpascal.net/cvpr2019/Chen_Multi-Label_Image_Recognition_With_Graph_Convolutional_Networks_CVPR_2019_paper.pdf)
> 透過GCN(Graph Convolution Networks)來尋找個標籤之相關性。

* [(2017) Image classification algorithm based on LTS-HD multi instance multi label RBF](https://ieeexplore.ieee.org/document/8282839)
* [(2019) Multi-Label Image Classification by Feature Attention Network](https://ieeexplore.ieee.org/abstract/document/8765716)
* [(2019) The Utilization of Multi-Label Samples For Hyperspectral Image Classification](https://ieeexplore.ieee.org/document/8898564)
:::

:::warning

:::