Sciweavers

2602 search results - page 240 / 521
» Semantic Analysis of 'to'
Sort
View
MM
2004
ACM
248views Multimedia» more  MM 2004»
16 years 3 days ago
Incremental semi-supervised subspace learning for image retrieval
Subspace learning techniques are widespread in pattern recognition research. They include Principal Component Analysis (PCA), Locality Preserving Projection (LPP), etc. These tech...
Xiaofei He
RIAO
2004
15 years 8 months ago
Chinese Character Expansion for Retrieving Japanese Paraphrases
This paper proposes two methods of query expansion for retrieving paraphrase candidates indexed by Kanzi (Chinese) characters. The idea is to calculate similarity between Kanzi ch...
Takenobu Tokunaga, Yoshiki Tezuka, Hozumi Tanaka
ICPR
2008
IEEE
16 years 7 months ago
Audio-visual event classification via spatial-temporal-audio words
In this paper, we propose a generative model-based approach for audio-visual event classification. This approach is based on a new unsupervised learning method using an extended p...
Ming Li, Sanqing Hu, Shih-Hsi Liu, Sung Baang, Yu ...
ICDAR
2007
IEEE
16 years 1 months ago
Context-Sensitive Error Correction: Using Topic Models to Improve OCR
Modern optical character recognition software relies on human interaction to correct misrecognized characters. Even though the software often reliably identifies low-confidence ...
Michael L. Wick, Michael G. Ross, Erik G. Learned-...
SAMT
2007
Springer
96views Multimedia» more  SAMT 2007»
16 years 23 days ago
LIVE: Semantic-based Multi-Stream Broadcasting of Media Events
—Broadcasting of media events is a real-time action demanding reliable just in time decisions based on the current content of incoming video streams and the availability of backg...
Tobias Bürger, Rupert Westenthaler, Christian...