Sciweavers

1575 search results - page 299 / 315
» Unsupervised Learning of Models for Recognition
Sort
View
PASTE
2010
ACM
15 years 2 months ago
Extracting compiler provenance from program binaries
We present a novel technique that identifies the source compiler of program binaries, an important element of program provenance. Program provenance answers fundamental questions...
Nathan E. Rosenblum, Barton P. Miller, Xiaojin Zhu
KDD
2010
ACM
233views Data Mining» more  KDD 2010»
15 years 1 months ago
Evolutionary hierarchical dirichlet processes for multiple correlated time-varying corpora
Mining cluster evolution from multiple correlated time-varying text corpora is important in exploratory text analytics. In this paper, we propose an approach called evolutionary h...
Jianwen Zhang, Yangqiu Song, Changshui Zhang, Shix...
102
Voted
ACL
2008
14 years 11 months ago
Semi-Supervised Sequential Labeling and Segmentation Using Giga-Word Scale Unlabeled Data
This paper provides evidence that the use of more unlabeled data in semi-supervised learning can improve the performance of Natural Language Processing (NLP) tasks, such as part-o...
Jun Suzuki, Hideki Isozaki
MM
2010
ACM
174views Multimedia» more  MM 2010»
14 years 9 months ago
Image classification using the web graph
Image classification is a well-studied and hard problem in computer vision. We extend a proven solution for classifying web spam to handle images. We exploit the link structure of...
Dhruv Kumar Mahajan, Malcolm Slaney
MVA
2006
205views Computer Vision» more  MVA 2006»
14 years 9 months ago
Ontological inference for image and video analysis
Abstract This paper presents an approach to designing and implementing extensible computational models for perceiving systems based on a knowledge-driven joint inference approach. ...
Christopher Town