开课单位--北京大学
<<<123>>> 2/3

11
A Longitudinal Study of Removed Apps in iOS App Store[iOS应用商店中被删除应用的纵向研究]
  Fuqi Lin(北京大学) A Longitudinal Study of Removed Apps in iOS App Store
热度:44

12
DeepRec: On-device Deep Learning for Privacy-Preserving Sequential Recommendation in Mobile Commerce[DeepRec:移动商务中隐私保护顺序推荐的设备上深度学习]
  Jialiang Han(北京大学) DeepRec: On-device Deep Learning for Privacy-Preserving Sequential Recommendation in Mobile Commerce
热度:97

13
Effective Multi-Label Active Learning for Text Classification[文本分类中的有效多标签主动学习]
  Bishan Yang(北京大学) Labeling text data is quite time-consuming but essential for automatic text classification. Especially, manually creating multiple labels for each doc...
热度:121

14
Measuring Visual Saliency by Site Entropy Rate[通过现场测量的视觉显着性的熵率]
  Yizhou Wang(北京大学) Propose a biology-inspired bottom-up computational model of attention based on Visual Saliency: –Information pursuit; –supported by ...
热度:112

15
Incorporating optical techniques in electron microscopy for comprehensive characterization of individual nanostructures[光学技术在电子显微镜中对单个纳米结构的综合表征]
  Min Gao(北京大学) The purpose of this informal talk is to introduce briefly some new additions to the research group at Peking University and seek more future collabora...
热度:57

17
Dirichlet Component Analysis: Feature Extraction for Compositional Data[狄利克雷成分分析:成分数据的特征提取]
  Hua-Yan Wang(北京大学) We consider feature extraction (dimensionality reduction) for compositional data, where the data vectors are constrained to be positive and constant-s...
热度:64

18
A Joint Segmenting and Labeling Approach for Chinese Lexical Analysis[一种联合分段和标注的中文词法分析方法]
  Xihong Wu; Jiazhong Nie; Xinhao Wang; Dingsheng Luo(北京大学) This paper introduces an approach which jointly performs a cascade of segmentation and labeling subtasks for Chinese lexical analysis, including word ...
热度:38

19
Dirichlet Aggregation: Unsupervised Learning towards an Optimal Metric for Proportional Data[狄利克雷聚合:无监督学习的比例数据的最佳度量]
  Hua-Yan Wang(北京大学) Proportional data (normalized histograms) have been frequently occurring in various areas, and they could be mathematically abstracted as points resid...
热度:50

20
A Fast and Performance-Maintained Transcoding Method based on Background Modeling for Surveillance Video[一种基于背景建模的监控视频快速性能保持转码方法]
  Xianguo Zhang(北京大学) Low-complexity and high-performance surveillance video transcoding methods play an important role for a wide range of surveillance video transmission ...
热度:41
<<<123>>> 2/3