Sciweavers

1443 search results - page 46 / 289
» Learning Generative Models via Discriminative Approaches
Sort
View
CVPR
2007
IEEE
14 years 11 months ago
Toward A Discriminative Codebook: Codeword Selection across Multi-resolution
In patch-based object recognition, there are two important issues on the codebook generation: (1) resolution: a coarse codebook lacks sufficient discriminative power, and an over-...
Lei Wang
HICSS
2006
IEEE
163views Biometrics» more  HICSS 2006»
14 years 2 months ago
Learning Ranking vs. Modeling Relevance
The classical (ad hoc) document retrieval problem has been traditionally approached through ranking according to heuristically developed functions (such as tf.idf or bm25) or gene...
Dmitri Roussinov, Weiguo Fan
NAACL
2010
13 years 6 months ago
Painless Unsupervised Learning with Features
We show how features can easily be added to standard generative models for unsupervised learning, without requiring complex new training methods. In particular, each component mul...
Taylor Berg-Kirkpatrick, Alexandre Bouchard-C&ocir...
ICMCS
2009
IEEE
103views Multimedia» more  ICMCS 2009»
13 years 6 months ago
Web image retrieval via learning semantics of query image
The performance of traditional image retrieval approaches remains unsatisfactory, as they are restricted by the wellknown semantic gap and the diversity of textual semantics. To t...
Chuanghua Gui, Jing Liu, Changsheng Xu, Hanqing Lu
ICML
2000
IEEE
14 years 1 months ago
Discriminative Reranking for Natural Language Parsing
This paper considers approaches which rerank the output of an existing probabilistic parser. The base parser produces a set of candidate parses for each input sentence, with assoc...
Michael Collins