论文笔记 | CNN-RNN:A Unified Framework for Multi-label Image Classification

最新推荐文章于 2024-08-01 23:00:00 发布

bea_tree

最新推荐文章于 2024-08-01 23:00:00 发布

阅读量7.3k

点赞数

文章标签： CNN-RNN

本文链接：https://blog.csdn.net/bea_tree/article/details/52688307

版权

Authors

Jiang Wang Yi Yang Junhua Mao Zhiheng Huang Chang Huang Wei Xu
Wang Jiang
这里写图片描述

Abstract

利用了CNN和RNN，考虑了类别之间的dependency，取得了不错的分类效果

1 Introduction

multi_label 的一些文献

Y. Gong, Y. Jia, T. Leung, A. Toshev, and S. Ioffe. Deep
convolutional ranking for multilabel image annotation. arXiv
preprint arXiv:1312.4894, 2013.

M. Guillaumin, T. Mensink, J. Verbeek, and C. Schmid.
Tagprop: Discriminative metric learning in nearest neighbor
models for image auto-annotation. In Computer Vision,
2009 IEEE 12th International Conference on, pages 309–
316. IEEE, 2009.

A. Makadia,