|本期目录/Table of Contents|

[1]邓远远,沈炜.基于注意力反馈机制的深度图像标注模型[J].浙江理工大学学报,2019,41-42(自科二):208-216.
 DENG Yuanyuan,SHEN Wei.Depth image caption model based on  attention feedback mechanism[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科二):208-216.
点击复制

基于注意力反馈机制的深度图像标注模型()
分享到:

浙江理工大学学报[ISSN:1673-3851/CN:33-1338/TS]

卷:
第41-42卷
期数:
2019年自科二期
页码:
208-216
栏目:
出版日期:
2019-04-23

文章信息/Info

Title:
Depth image caption model based on  attention feedback mechanism
文章编号:
1673-3851 (2019) 03-0208-09
作者:
邓远远沈炜
浙江理工大学信息学院,杭州 310018
Author(s):
DENG YuanyuanSHEN Wei
School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China
关键词:
卷积神经网络深度学习图像识别注意力机制
分类号:
TP181
文献标志码:
A
摘要:
针对图像标注任务提出了一种基于注意力反馈机制的深度图像标注模型。该模型采用编码器解码器框架;编码器采用VGG16的网络结构,以提取图像的特征信息;在解码器部分设计了一种堆叠方式自上而下的处理注意力信息,使网络的每一层都可以获得额外的特征信息。然后从生成的标注语句中提取特征,将关注特征和图像的关注区域结合,增强和图像关注区域的匹配性,使生成的标注语句近似真实语境。在Flickr8k、Flickr30k和MSCOCO等数据集进行实验,实验结果显示,所提出模型的识别率比经典图像识别模型高5%~9%。

参考文献/References:

[1] Plis S M, Hjelm D R, Salakhutdinov R, et al. Deep learning for neuroimaging: a validation study[J]. Frontiers in neuroscience, 2014, 8(8): 00229.
[2] Roth H R, Lu L, Seff A, et al. A new 25 D representation for lymph node detection using random sets of deep convolutional neural network observations[C]//International Conference on Medical Image Computing and ComputerAssisted Intervention. Springer, 2014: 520-527.
[3] Bernardi R, Cakici R, Elliott D, et al. Automatic description generation from images: A survey of models, datasets, and evaluation measures[J]. Journal of Artificial Intelligence Research, 2016, 55: 409-442.
[4] Hodosh M, Young P, Hockenmaier J. Framing image description as a ranking task: Data, models and evaluation metrics[J]. Journal of Artificial Intelligence Research, 2013, 47: 853-899.
[5] Gong Y, Wang L, Hodosh M, et al. Improving imagesentence embeddings using large weakly annotated photo collections[C]//European Conference on Computer Vision. Springer, 2014: 529-545.
[6] Cho K, Van Merrinboer B, Gulcehre C, et al. Learning phrase representations using RNN encoderdecoder for statistical machine translation. (2014-09-03) [ 2018-12-06]. https://arxiv.org/abs/1406-1078.
[7] Fang F, Wang H, Chen Y, et al. Looking deeper and transferring attention for image captioning[J]. Multimedia Tools and Applications, 2018(8): 1-17.
[8] Chang Y S. Finegrained attention for image caption generation[J]. Multimedia Tools and Applications, 2018, 77(3): 2959-2971.
[9] Vinyals O, Toshev A, Bengio S, et al. Show and tell: A neural image caption generator[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE, 2015: 3156-3164.
[10] Mojoo J, Kurosawa K, Kurita T. Deep CNN with graph Laplacian regularization for multilabel image annotation[C]//International Conference Image Analysis and Recognition. Springer, 2017: 19-26.

相似文献/References:

[1]李斯凡,高法钦.基于卷积神经网络的手写数字识别[J].浙江理工大学学报,2017,37-38(自科3):438.
 LI Sifan,GAO Faqin.Handwritten Numeral Recognition Based on Convolution Neural Network[J].Journal of Zhejiang Sci-Tech University,2017,37-38(自科二):438.
[2]张玮,张华熊.基于卷积神经网络的纺织面料主成分分类[J].浙江理工大学学报,2019,41-42(自科一):1.
 ZHANG Wei,ZHANG Huaxiong.Classification of main components of textile fabrics based on convolutional neural network[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科二):1.
[3]包晓安,徐海,张娜,等.基于深度学习的语音识别模型及其在智能家居中的应用[J].浙江理工大学学报,2019,41-42(自科二):217.
 BAO Xiaoan,XU Hai,ZHANG Na,et al.Speech recognition model based on deep learning and its application in smart home[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科二):217.
[4]包晓安,高春波,张娜,等.基于生成对抗网络的图像超分辨率方法[J].浙江理工大学学报,2019,41-42(自科四):499.
 BAO Xiaoan,GAO Chunbo,ZHANG Na,et al.Image superresolution method based ongenerative adversarial network[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科二):499.
[5]陈巧红,王磊,孙麒,等.基于混合神经网络的中文短文本分类模型[J].浙江理工大学学报,2019,41-42(自科四):509.
 CHEN Qiaohong,WANG Lei,SUN Qi,et al.Chinese short text classification model based on hybrid neural network[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科二):509.
[6]陈巧红,陈翊,孙麒,等.服装图像分类技术综述[J].浙江理工大学学报,2019,41-42(自科五):631.
 CHEN Qiaohong,CHEN Yi,SUN Qi,et al.Overview of clothing image classification technology[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科二):631.
[7]程诚,任佳.基于自适应卷积核的改进CNN数值型数据分类算法[J].浙江理工大学学报,2019,41-42(自科五):657.
 CHENG Cheng,REN Jia.Improved CNN classification algorithm based on adaptive convolution kernel for numerical data[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科二):657.
[8]邓远远,沈炜.基于注意力反馈机制的深度图像标注模型[J].浙江理工大学学报,2019,41-42(自科二):208.
 DENG Yuanyuan,SHEN Wei.Depth image caption model based on attention feedback mechanism[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科二):208.
[9]陈巧红,董雯,孙麒,等.基于混合神经网络的单文档自动文摘模型[J].浙江理工大学学报,2019,41-42(自科四):489.
 CHEN Qiaohong,DONG Wen,SUN Qi,et al.Single document automatic summarization model based on hybrid neural network[J].Journal of Zhejiang Sci-Tech University,2019,41-42(自科二):489.

备注/Memo

备注/Memo:
收稿日期: 2018-09-08
网络出版日期: 2018-12-28
作者简介:邓远远(1992-),男,河南安阳人,硕士研究生,主要从事图像识别方面的研究
通信作者:沈炜,E-mail:120259565@qq.com
更新日期/Last Update: 2019-03-19