Sciweavers

598 search results - page 48 / 120
» Experiments with Classifier Combining Rules
Sort
View
ICMCS
2005
IEEE
108views Multimedia» more  ICMCS 2005»
15 years 8 months ago
Robust learning-based TV commercial detection
A robust learning-based TV commercial detection approach is proposed in this paper. Firstly a set of basic features that facilitate distinguishing commercials from general program...
Xian-Sheng Hua, Lie Lu, Hong-Jiang Zhang
124
Voted
CVPR
2010
IEEE
15 years 11 months ago
Learning from Interpolated Images using Neural Networks for Digital Forensics
Interpolated images have data redundancy, and special correlation exists among neighboring pixels, which is a crucial clue in digital forensics. We design a neural network based f...
Yizhen Huang, Na Fan
109
Voted
ICDAR
2003
IEEE
15 years 8 months ago
Rejection Algorithm for Mis-segmented Characters In Multilingual Document Recognition
In OCR systems the character segmentation algorithm may generate mis-segmented blocks. Feedback information from character classifier is indispensable to achieve higher character ...
Zhengang Chen, Xiaoqing Ding
112
Voted
CIARP
2008
Springer
15 years 4 months ago
Learning and Forgetting with Local Information of New Objects
The performance of supervised learners depends on the presence of a relatively large labeled sample. This paper proposes an automatic ongoing learning system, which is able to inco...
Fernando Vázquez, José Salvador S&aa...
142
Voted
ACL
2009
15 years 15 days ago
Semantic Tagging of Web Search Queries
We present a novel approach to parse web search queries for the purpose of automatic tagging of the queries. We will define a set of probabilistic context-free rules, which genera...
Mehdi Manshadi, Xiao Li