A Deep Multi-Modal CNN for Multi-Instance Multi-Label Image Classification.

IEEE Transactions on Image Processing(2018)

引用 96|浏览77
暂无评分
摘要
Deep convolutional neural networks (CNNs) have shown superior performance on the task of single-label image classification. However, the applicability of CNNs to multi-label images still remains an open problem, mainly because of two reasons. First, each image is usually treated as an inseparable entity and represented as one instance, which mixes the visual information corresponding to different ...
更多
查看译文
关键词
Image classification,Feature extraction,Convolutional neural networks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要