咨询与建议

限定检索结果

文献类型

  • 39 篇 期刊文献
  • 17 篇 会议
  • 1 篇 学位论文

馆藏范围

  • 57 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 52 篇 工学
    • 45 篇 计算机科学与技术...
    • 16 篇 电气工程
    • 5 篇 软件工程
    • 2 篇 控制科学与工程
    • 1 篇 电子科学与技术(可...
    • 1 篇 信息与通信工程
    • 1 篇 水利工程
    • 1 篇 环境科学与工程(可...
    • 1 篇 生物医学工程(可授...
    • 1 篇 生物工程
  • 7 篇 理学
    • 5 篇 生物学
    • 2 篇 物理学
    • 1 篇 数学
    • 1 篇 统计学(可授理学、...
  • 5 篇 医学
    • 2 篇 基础医学(可授医学...
    • 2 篇 特种医学
    • 1 篇 临床医学
  • 4 篇 管理学
    • 4 篇 管理科学与工程(可...
  • 3 篇 农学
    • 1 篇 作物学
  • 1 篇 教育学
    • 1 篇 教育学

主题

  • 57 篇 multi-instance m...
  • 8 篇 machine learning
  • 7 篇 protein function...
  • 4 篇 neural networks
  • 4 篇 scene classifica...
  • 3 篇 text categorizat...
  • 3 篇 ensemble learnin...
  • 3 篇 deep learning
  • 3 篇 radial basis fun...
  • 3 篇 feature extracti...
  • 3 篇 training
  • 2 篇 model interpreta...
  • 2 篇 sequence-level
  • 2 篇 multi-label lear...
  • 2 篇 task analysis
  • 2 篇 breast histopath...
  • 2 篇 genome wide
  • 2 篇 image annotation
  • 2 篇 brain ct
  • 2 篇 label correlatio...

机构

  • 5 篇 nanjing univ nat...
  • 4 篇 shandong inst bu...
  • 3 篇 nanjing univ sta...
  • 3 篇 ludong univ sch ...
  • 2 篇 south china univ...
  • 2 篇 shandong univ sc...
  • 2 篇 beijing inst tec...
  • 2 篇 china univ petr ...
  • 2 篇 nanjing univ pos...
  • 2 篇 peng cheng lab p...
  • 2 篇 dalian univ tech...
  • 1 篇 univ sci & techn...
  • 1 篇 nanjing univ sof...
  • 1 篇 south china univ...
  • 1 篇 southwest petr u...
  • 1 篇 hong kong polyte...
  • 1 篇 univ salford sch...
  • 1 篇 univ aizu comp s...
  • 1 篇 georgia inst tec...
  • 1 篇 nanjing univ pos...

作者

  • 5 篇 zhou zhi-hua
  • 4 篇 huang sheng-jun
  • 3 篇 wu qingyao
  • 2 篇 shi guoqiang
  • 2 篇 chen tongtong
  • 2 篇 liu ying
  • 2 篇 yang yang
  • 2 篇 ding xinmiao
  • 2 篇 gu hong
  • 2 篇 liu chan-juan
  • 2 篇 xu xinshun
  • 2 篇 he jianjun
  • 2 篇 min huaqing
  • 2 篇 raich raviv
  • 2 篇 zou hailin
  • 2 篇 li yunjie
  • 2 篇 liu chanjuan
  • 2 篇 chen tong-tong
  • 2 篇 pan zesi
  • 2 篇 wang zhelong

语言

  • 56 篇 英文
  • 1 篇 中文
检索条件"主题词=Multi-instance Multi-label Learning"
57 条 记 录,以下是51-60 订阅
排序:
A multi-instance multi-label Scene Classification Method based on multi-Kernel Fusion
A Multi-Instance Multi-Label Scene Classification Method bas...
收藏 引用
SAI Intelligent Systems Conference (IntelliSys)
作者: Chen Tong-tong Liu Chan-juan Zou Hai-lin Zhou Shu-sen Liu Ying Ding Xin-miao Ludong Univ Sch Informat & Elect Engn Yantai Peoples R China Shandong Inst Business & Technol Sch Informat & Elect Engn Yantai Peoples R China
multi-instance multi-label learning, an extension of multi-instance learning in multi-label classification, has been successfully used in image classification. In existing algorithms, the distribution of instances in ... 详细信息
来源: 评论
Improvement of learning Algorithm for the multi-instance multi-label RBF Neural Networks Trained with Imbalanced Samples
收藏 引用
JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 2013年 第4期29卷 765-776页
作者: Li, Cunhe Shi, Guoqiang China Univ Petr Coll Comp & Commun Engn Qingdao 266555 Peoples R China
multi-instance multi-label learning (MIML) is a novel learning framework where each sample is represented by multiple instances and associated with multiple class labels. In several learning situations, the multi-inst... 详细信息
来源: 评论
MIMLRBF: RBF neural networks for multi-instance multi-label learning
收藏 引用
NEUROCOMPUTING 2009年 第16-18期72卷 3951-3956页
作者: Zhang, Min-Ling Wang, Zhi-Jian Hohai Univ Coll Comp & Informat Engn Nanjing 210098 Peoples R China
In multi-instance multi-label learning (MIML), each example is not only represented by multiple instances but also associated with multiple class labels. Several learning frameworks, such as the traditional supervised... 详细信息
来源: 评论
Weights optimization for multi-instance multi-label RBF neural networks using steepest descent method
收藏 引用
NEURAL COMPUTING & APPLICATIONS 2013年 第7-8期22卷 1563-1569页
作者: Li, Cunhe Shi, Guoqiang China Univ Petr Coll Comp & Commun Engn Qingdao 266555 Peoples R China
multi-instance multi-label learning (MIML) is an innovative learning framework where each sample is represented by multiple instances and associated with multiple class labels. In several learning situations, the mult... 详细信息
来源: 评论
multi-instance multi-label image classification: A neural approach
收藏 引用
NEUROCOMPUTING 2013年 99卷 298-306页
作者: Chen, Zenghai Chi, Zheru Fu, Hong Feng, Dagan Hong Kong Polytech Univ Elect & Informat Engn Dept Ctr Multimedia Signal Proc Kowloon Hong Kong Peoples R China Chu Hai Coll Higher Educ Dept Comp Sci Tsuen Wan Hong Kong Peoples R China Univ Sydney Sch Informat Technol Sydney NSW 2006 Australia Univ Sydney Inst Biomed Engn & Technol Sydney NSW 2006 Australia
In this paper, a multi-instance multi-label algorithm based on neural networks is proposed for image classification. The proposed algorithm, termed multi-instance multi-label neural network (MIMLNN), consists of two s... 详细信息
来源: 评论
Categorization of multiple Objects in a Scene Using a Biased Sampling Strategy
收藏 引用
INTERNATIONAL JOURNAL OF COMPUTER VISION 2013年 第1期105卷 1-18页
作者: Yang, Lei Zheng, Nanning Chen, Mei Yang, Yang Yang, Jie Xi An Jiao Tong Univ China Mobile Res Inst Beijing 100053 Peoples R China Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian 710049 Peoples R China Intel Labs Pittsburgh Pittsburgh PA 15213 USA Carnegie Mellon Univ Pittsburgh PA 15213 USA
Recently, various bag-of-features (BoF) methods show their good resistance to within-class variations and occlusions in object categorization. In this paper, we present a novel approach for multi-object categorization... 详细信息
来源: 评论
A Novel Approach for Automatic Image Annotation Using Enhanced multi-instance Differentiation Framework
收藏 引用
Procedia Engineering 2012年 38卷 2694-2701页
作者: T. Sumadhi M. Hemalatha Research Scholar Karpagam UniversityCoimbatore Prof. & Head Department of software systems Karpagam UniversityCoimbatore
With the rapid development of digital cameras, we have witnessed great interest and promise in automatic image annotation as a hot research field. Automatic image annotation is an effective method to resolve the probl... 详细信息
来源: 评论