810 search results - page 97 / 162 » Learning to Segment Document Images |
EMNLP
2007
13 years 10 months ago
2007
We present two machine learning approaches to information extraction from semi-structured documents that can be used if no annotated training data are available, but there does ex...
PR
2008
13 years 8 months ago
2008
Semantic-based image retrieval has attracted great interest in recent years. This paper proposes a region-based image retrieval system with high-level semantic learning. The key f...
MLMI
2004
Springer
14 years 2 months ago
2004
Springer
This paper presents a shallow dialogue analysis model, aimed at human-human dialogues in the context of staff or business meetings. Four components of the model are defined, and ...
ACML
2009
Springer
14 years 3 months ago
2009
Springer
Abstract. Topic models are a discrete analogue to principle component analysis and independent component analysis that model topic at the word level within a document. They have ma...
ICCV
2007
IEEE
14 years 10 months ago
2007
IEEE
Convolutional networks have achieved a great deal of success in high-level vision problems such as object recognition. Here we show that they can also be used as a general method ...