Sciweavers

CVPR
2012
IEEE
11 years 10 months ago
Detection by detections: Non-parametric detector adaptation for a video
We propose an approach to improving the detection results of a generic offline trained detector on a specific video. Our method does not leverage visual tracking as most detecti...
Xiaoyu Wang, Gang Hua, Tony X. Han
CVPR
2012
IEEE
11 years 10 months ago
Robust visual domain adaptation with low-rank reconstruction
Visual domain adaptation addresses the problem of adapting the sample distribution of the source domain to the target domain, where the recognition task is intended but the data d...
I-Hong Jhuo, Dong Liu, D. T. Lee, Shih-Fu Chang
ICASSP
2011
IEEE
12 years 11 months ago
Relevance language modeling for speech recognition
Language models for speech recognition tend to be brittle across domains, since their performance is vulnerable to changes in the genre or topic of the text on which they are trai...
Kuan-Yu Chen, Berlin Chen