Sciweavers

295 search results - page 56 / 59
» An SVM based classification approach to speech separation
Sort
View
AIR
2004
113views more  AIR 2004»
13 years 7 months ago
Class Noise vs. Attribute Noise: A Quantitative Study
Real-world data is never perfect and can often suffer from corruptions (noise) that may impact interpretations of the data, models created from the data and decisions made based on...
Xingquan Zhu, Xindong Wu
CIVR
2003
Springer
200views Image Analysis» more  CIVR 2003»
14 years 19 days ago
Multimedia Search with Pseudo-relevance Feedback
We present an algorithm for video retrieval that fuses the decisions of multiple retrieval agents in both text and image modalities. While the normalization and combination of evi...
Rong Yan, Alexander G. Hauptmann, Rong Jin
IJCNN
2006
IEEE
14 years 1 months ago
Adaptation of Artificial Neural Networks Avoiding Catastrophic Forgetting
— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...
Dario Albesano, Roberto Gemello, Pietro Laface, Fr...
FUIN
2007
129views more  FUIN 2007»
13 years 7 months ago
Sound Isolation by Harmonic Peak Partition For Music Instrument Recognition
Abstract. Identification of music instruments in polyphonic sounds is difficult and challenging, especially where heterogeneous harmonic partials are overlapping with each other....
Xin Zhang, Zbigniew W. Ras
ICSE
2005
IEEE-ACM
14 years 7 months ago
Static analysis tools as early indicators of pre-release defect density
During software development it is helpful to obtain early estimates of the defect density of software components. Such estimates identify fault-prone areas of code requiring furth...
Nachiappan Nagappan, Thomas Ball