End-to-End Automatic Image Annotation Based on Deep CNN and Multi-Label Data Augmentation
Authors:
- Xiao KeXKXiao Ke
- Jiawei ZouJZJiawei Zou
- Yuzhen NiuYNYuzhen Niu
- 25 January 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 21 (8) , 2093-2106
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (61502105, 61672158)
- Technology Guidance Project of Fujian Province (2017H0015)
- Natural Science Foundation of Fujian Province (2018J1798)
- University Production Project of Fujian Province (2017H6008)
- Fujian Collaborative Innovation Center for Big Data Application in Governments
This publication has 38 references indexed in Scilit:
- Social Diffusion Analysis With Common-Interest Model for Image AnnotationIEEE Transactions on Multimedia, 2015
- Efficient multi-modal fusion on supergraph for scalable image annotationPattern Recognition, 2015
- ANNOR: Efficient image annotation based on combining local and global featuresComputers & Graphics, 2015
- A comparative study of different feature mapping methods for image annotation2015
- Image annotation based on feature fusion and semantic similarityNeurocomputing, 2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- MLRank: Multi-correlation Learning to Rank for image annotationPattern Recognition, 2013
- Random Forest for Image Annotation2012
- A New Baseline for Image Annotation2008
- Multiple Bernoulli relevance models for image and video annotation2004