QQ客服 官方微博 反馈留言

浏览/检索结果: 共37条，第1-10条 帮助 限定条件 专题：西安交通大学    第一署名单位    第一作者单位    通讯作者单位     已选(0)清除 条数/页：5101520253035404550556065707580859095100   排序方式：请选择作者升序作者降序题名升序题名降序发表日期升序发表日期降序提交时间升序提交时间降序 Fine-Grained Image Classification Using Modified DCNNs Trained by Cascaded Softmax and Generalized Large-Margin Losses 期刊论文 IEEE Transactions on Neural Networks and Learning Systems, 2019, 卷号: 30, 页码: 683-694 作者:  Shi, Weiwei;  Gong, Yihong;  Tao, Xiaoyu;  Cheng, De;  Zheng, Nanning 收藏  |  浏览/下载：10/0  |  提交时间：2019/11/19 Benchmark testing  Classification accuracy  Classification framework  Deep convolutional neural networks  Experimental evaluation  Fine grained  Large margins  Within-class variances   A Graph-Based Semisupervised Deep Learning Model for PolSAR Image Classification 期刊论文 IEEE Transactions on Geoscience and Remote Sensing, 2019, 卷号: 57, 页码: 2116-2132 作者:  Bi, Haixia;  Sun, Jian;  Xu, Zongben 收藏  |  浏览/下载：22/0  |  提交时间：2019/11/19 Convolutional Neural Networks (CNN)  Graph model  Image edge detection  Polarimetric synthetic aperture radars  Prediction algorithms  Semi-supervised method  Task analysis   An Energy-Efficient and Flexible Accelerator based on Reconfigurable Computing for Multiple Deep Convolutional Neural Networks 会议论文 作者:  Yang, Chen;  Zhang, HaiBo;  Wang, XiaoLi;  Geng, Li 收藏  |  浏览/下载：4/0  |  提交时间：2019/11/19 CNN  Zero Detection Technology  Image Row Broadcast dataflow  Reconfigurable computing   Transductive Semi-Supervised Deep Learning Using Min-Max Features 会议论文 作者:  Shi, Weiwei;  Gong, Yihong;  Ding, Chris;  Ma, Zhiheng;  Tao, Xiaoyu 收藏  |  浏览/下载：5/0  |  提交时间：2019/11/19 Classification accuracy  Confidence levels  Deep convolutional neural networks  Feature descriptors  Min-max  Semi-supervised  Semi-supervised learning (SSL)  Transductive learning   A Visual System of Citrus Picking Robot Using Convolutional Neural Networks 会议论文 作者:  Liu, Yan-Ping;  Mabu, Shingo;  Yang, Chang-Hui;  Kuremoto, Takashi;  Ling, Huang 收藏  |  浏览/下载：6/0  |  提交时间：2019/11/26 citrus harvesting robot  YOLOv3  Mask R-CNN  deep learning   Spatial-temproal based lane detection using deep learning 会议论文 作者:  Huang, Yuhao;  Chen, Shitao;  Chen, Yu;  Jian, Zhiqiang;  Zheng, Nanning 收藏  |  浏览/下载：2/0  |  提交时间：2019/11/26 Boundary detection method  Convolutional neural network  Convolutional Neural Networks (CNN)  Environment conditions  Lane detection  Perspective transforms  Spatial-temporal correlation  State-of-the-art methods   Fast Single Image Super-Resolution via Dilated Residual Networks 期刊论文 IEEE Access, 2018 作者:  Lu, Zhang;  Yu, Zhang;  Ya-Li, Peng;  Shi-Gang, Liu;  Xiaojun, Wu 收藏  |  浏览/下载：2/0  |  提交时间：2019/11/26 Convergence  Convolutional neural network  Deep convolutional neural networks  Exponential expansion  Image super resolutions  Image super-resolution  Real time performance  residual learning   Background Subtraction Algorithm With Bayesian Generative Adversarial Networks 期刊论文 Zidonghua Xuebao/Acta Automatica Sinica, 2018, 卷号: 44, 页码: 878-890 作者:  Zheng, Wen-Bo;  Wang, Kun-Feng;  Wang, Fei-Yue 收藏  |  浏览/下载：2/0  |  提交时间：2019/11/26 Adversarial networks  Background extraction  Background subtraction  Background subtraction algorithms  Deep convolutional neural networks  Illumination changes  Median filtering algorithm  Non-stationary backgrounds   Machinery health indicator construction based on convolutional neural networks considering trend burr 期刊论文 NEUROCOMPUTING, 2018, 卷号: 292, 页码: 142-150 作者:  Guo, Liang;  Lei, Yaguo;  Li, Naipeng;  Yan, Tao;  Li, Ningbo 收藏  |  浏览/下载：7/0  |  提交时间：2019/11/26 Deep learning  Machinery health indicator  Convolutional neural network  Outlier region correction  Trend burr   Training DCNN by Combining Max-Margin, Max-Correlation Objectives, and Correntropy Loss for Multilabel Image Classification 期刊论文 IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 卷号: 29, 页码: 2896-2908 作者:  Shi, Weiwei;  Gong, Yihong;  Tao, Xiaoyu;  Zheng, Nanning 收藏  |  浏览/下载：7/0  |  提交时间：2019/11/26 deep convolutional neural network (DCNN)  multilabel image classification  max-margin objective  max-correlation objective  Correntropy loss