Sciweavers

778 search results - page 44 / 156
» Frame domain signal processing: Framework and applications
Sort
View
AVSS
2007
IEEE
15 years 6 months ago
Compact representation and probabilistic classification of human actions in videos
This paper addresses the problem of classifying human actions in a video sequence. A representation eigenspace approach based on the PCA algorithm is used to train the classifier...
Carlo Colombo, Dario Comanducci, Alberto Del Bimbo
91
Voted
ICASSP
2010
IEEE
15 years 20 days ago
Towards multi-speaker unsupervised speech pattern discovery
In this paper, we explore the use of a Gaussian posteriorgram based representation for unsupervised discovery of speech patterns. Compared with our previous work, the new approach...
Yaodong Zhang, James R. Glass
92
Voted
ICASSP
2011
IEEE
14 years 4 months ago
A single-channel noise reduction MVDR filter
Most existing approaches for single-channel noise reduction in the frequency domain via the short-time Fourier transform (STFT) assume that consecutive time-frames are uncorrelate...
Jacob Benesty, Yiteng Huang
SIPS
2007
IEEE
15 years 6 months ago
Robust Region-of-Interest Scalable Coding with Leaky Prediction in H.264/AVC
We propose a region-of-interest (ROI) coding framework based on leaky prediction (LP) for robustly transporting H.264 video over error-prone network. The LP-based ROI coding can r...
Qian Chen, Li Song, Xiaokang Yang, Wenjun Zhang
ICIP
2009
IEEE
16 years 1 months ago
Spatial And Temporal Up-conversion Technique For Depth Video
This paper proposes a novel framework for up-conversion of depth video resolution both in spatial and in time domain. Time-of-Flight (TOF) sensors are widely used in computer visi...