Sciweavers

978 search results - page 2 / 196
» Adapting Visual Category Models to New Domains
Sort
View
IJCAI
2007
13 years 6 months ago
Incremental Learning of Perceptual Categories for Open-Domain Sketch Recognition
Most existing sketch understanding systems require a closed domain to achieve recognition. This paper describes an incremental learning technique for opendomain recognition. Our s...
Andrew M. Lovett, Morteza Dehghani, Kenneth D. For...
SIGIR
2002
ACM
13 years 5 months ago
A new family of online algorithms for category ranking
We describe a new family of topic-ranking algorithms for multi-labeled documents. The motivation for the algorithms stems from recent advances in online learning algorithms. The a...
Koby Crammer, Yoram Singer
IJCNLP
2005
Springer
13 years 10 months ago
Adapting a Probabilistic Disambiguation Model of an HPSG Parser to a New Domain
Abstract. This paper describes a method of adapting a domain-independent HPSG parser to a biomedical domain. Without modifying the grammar and the probabilistic model of the origin...
Tadayoshi Hara, Yusuke Miyao, Jun-ichi Tsujii
VL
2006
IEEE
170views Visual Languages» more  VL 2006»
13 years 11 months ago
A Lightweight Model for End Users' Domain-Specific Data
Many end user programming tools lack adequate support for domain-specific data. We will design a lightweight representation for categories of data, called “topes,” and develop...
Christopher Scaffidi
EPIA
2009
Springer
13 years 12 months ago
Learning Visual Object Categories with Global Descriptors and Local Features
Different types of visual object categories can be found in real-world applications. Some categories are very heterogeneous in terms of local features (broad categories) while oth...
Rui Pereira, Luís Seabra Lopes