中国科学院机构知识库网格系统: 检索

Enhance prototypical networks with hybrid attention and confusing loss function for few-shot relation classification 期刊论文 OAI收割
NEUROCOMPUTING, 2022, 卷号: 493
作者: Li, Yibing; Ma, Zuchang; Gao, Lisheng; Wu, Yichen; Xie, Fei

|

收藏 | 浏览/下载：30/0 | 提交时间：2022/12/23

Relation classification Few-shot learning Hybrid attention Loss BERT

Sample-based online learning for bi-regular hinge loss 期刊论文 OAI收割
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2021, 页码: 16
作者: Xue, Wei; Zhong, Ping; Zhang, Wensheng; Yu, Gaohang; Chen, Yebin

|

收藏 | 浏览/下载：27/0 | 提交时间：2021/03/08

SVM Max-margin classification Hinge loss Elastic net Online learning

Fault Classification for On-board Equipment of High-speed Railway Based on Attention Capsule Network 期刊论文 OAI收割
International Journal of Automation and Computing, 2021, 卷号: 18, 期号: 5, 页码: 814-825
作者: Lu-Jie Zhou

|

收藏 | 浏览/下载：23/0 | 提交时间：2021/09/13

On-board equipment fault classification capsule network attention mechanism focal loss

CR-Net: A Deep Classification-Regression Network for Multimodal Apparent Personality Analysis 期刊论文 OAI收割
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2020, 页码: 18
作者: Li, Yunan; Wan, Jun; Miao, Qiguang; Escalera, Sergio; Fang, Huijuan

|

收藏 | 浏览/下载：55/0 | 提交时间：2020/06/02

Personality traits Multimodal data Convolutional neural networks Classification-regression network Bell Loss function

Implicit Negative Sub-Categorization and Sink Diversion for Object Detection 期刊论文 OAI收割
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 卷号: 27, 期号: 4, 页码: 1561-1574
作者: Li, Yu; Tang, Sheng; Lin, Min; Zhang, Yongdong; Li, Jintao

|

收藏 | 浏览/下载：44/0 | 提交时间：2019/12/10

Object detection convolutional neural network faster R-CNN classification loss context information

Research on Optimization Method of Deep Neural Network 会议论文 OAI收割
LIDAR IMAGING DETECTION AND TARGET RECOGNITION 2017, Changchun, China, July 23-25, 2017
作者: Zhao HC(赵怀慈); Liu PF(刘鹏飞); Cao FD(曹飞道)

|

收藏 | 浏览/下载：24/0 | 提交时间：2017/12/21

Deep neural network object classification over-fitting loss function

Ramp loss least squares support vector machine 期刊论文 iSwitch采集
Journal of computational science, 2016, 卷号: 14, 页码: 61-68
作者: Liu, Dalian; Shi, Yong; Tian, Yingjie; Huang, Xiankai

收藏 | 浏览/下载：41/0 | 提交时间：2019/05/09

Least squares support vector machine Sparse Ramp loss Cccp Classification

Pedotransfer Functions for Estimating Soil Bulk Density: A Case Study in the Three-River Headwater Region of Qinghai Province, China SCI/SSCI论文 OAI收割
2016
作者: Yi X. S.; Li, G. S.; Yin, Y. Y.

|

收藏 | 浏览/下载：30/0 | 提交时间：2017/11/09

alpine soil artificial neural network multiple linear regression organic carbon soil depth soil texture artificial neural-network water-retention curves organic-matter content hydraulic conductivity forest soils ignition loss carbon classification prediction taxonomy

Pedotransfer Functions for Estimating Soil Bulk Density: A Case Study in the Three-River Headwater Region of Qinghai Province, China SCI/SSCI论文 OAI收割
2016
作者: Yi X. S.; Li, G. S.; Yin, Y. Y.

收藏 | 浏览/下载：27/0 | 提交时间：2016/12/16

alpine soil artificial neural network multiple linear regression organic carbon soil depth soil texture artificial neural-network water-retention curves organic-matter content hydraulic conductivity forest soils ignition loss carbon classification prediction taxonomy

A segment detection method based on improved Hough transform (EI CONFERENCE) 会议论文 OAI收割
ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China
作者: Yao Z.-J.

收藏 | 浏览/下载：29/0 | 提交时间：2013/03/25

Hough transform is recognized as a powerful tool in shape analysis which gives good results even in the presence of noise and the disconnection of edge. However 3. applying the standard Hough transform equation to every point of the input image edge 4. according to the local threshold 6. merging the segments whose extreme points are near. Experiment results show the approach not only can recognize regular geometric object but also can extract the segment feature of real targets in complex environment. So the proposed method can be used in the target detection of complicated scenes traditional Hough transform can only detect the lines 2. quantizing the parameter space and extracting a group of maximums according to the global threshold eliminating spurious peaks which are caused by the spreading effects and will improve the precision of tracking. cannot give the endpoints and length of the line segments and it is vulnerable to the quantization errors. Based on the analysis of its limitations Hough transform has been improved in order to detect line segment feature of targets. The algorithm aims to avoid the loss of spatial information as well as to eliminate the spurious peaks and fix on the line segments endpoints accurately 5. fixing on the endpoints of the segments according to the dynamic clustering rule which can expediently be used for the description and classification of regular objects. The method consists of 6 steps: 1. setting up the image parameter and line-segment spaces