Sciweavers

1437 search results - page 206 / 288
» Recognition Using Region Correspondences
Sort
View
188
Voted
ICASSP
2011
IEEE
14 years 11 months ago
Design of UEP-based MSE-minimizing rateless codes for source-channel coding
This paper proposes a method to optimize the performance of tandem source–channel coding with respect to the mean-squared error by exploiting the unequal error protection coding...
Amirpasha Shirazinia, Lei Bao, Mikael Skoglund
188
Voted
UAI
2003
15 years 8 months ago
On Triangulating Dynamic Graphical Models
This paper introduces improved methodology to triangulate dynamic graphical models and dynamic Bayesian networks (DBNs). In this approach, a standard DBN template can be modified...
Jeff A. Bilmes, Chris Bartels
TASLP
2008
141views more  TASLP 2008»
15 years 7 months ago
Unsupervised Pattern Discovery in Speech
We present a novel approach to speech processing based on the principle of pattern discovery. Our work represents a departure from traditional models of speech recognition, where t...
A. S. Park, J. R. Glass
WWW
2011
ACM
15 years 1 months ago
Two-stream indexing for spoken web search
This paper presents two-stream processing of audio to index the audio content for Spoken Web search. The first stream indexes the meta-data associated with a particular audio doc...
Jitendra Ajmera, Anupam Joshi, Sougata Mukherjea, ...
192
Voted

Publication
262views
16 years 11 months ago
Attribute Multiset Grammars for Global Explanations of Activities
Recognizing multiple interleaved activities in a video requires implicitly partitioning the detections for each activity. Furthermore, constraints between activities are important ...
Dima Damen, David Hogg