Sciweavers

111 search results - page 21 / 23
» trecvid 2008
Sort
View
PAMI
2008
146views more  PAMI 2008»
13 years 9 months ago
Video Event Recognition Using Kernel Methods with Multilevel Temporal Alignment
In this work, we systematically study the problem of event recognition in unconstrained news video sequences. We adopt the discriminative kernel-based method for which video clip s...
Dong Xu, Shih-Fu Chang
VLSISP
2010
106views more  VLSISP 2010»
13 years 8 months ago
A Multi-Pronged Approach to Improving Semantic Extraction of News Video
In this paper we describe a multi-strategy approach to improving semantic extraction from news video. Experiments show the value of careful parameter tuning, exploiting multiple fe...
Alexander G. Hauptmann, Ming-yu Chen, Michael G. C...
CIVR
2009
Springer
132views Image Analysis» more  CIVR 2009»
14 years 4 months ago
Real-time bag of words, approximately
We start from the state-of-the-art Bag of Words pipeline that in the 2008 benchmarks of TRECvid and PASCAL yielded the best performance scores. We have contributed to that pipelin...
Jasper R. R. Uijlings, Arnold W. M. Smeulders, Rem...
TMM
2010
231views Management» more  TMM 2010»
13 years 4 months ago
Real-Time Visual Concept Classification
As datasets grow increasingly large in content-based image and video retrieval, computational efficiency of concept classification is important. This paper reviews techniques to ac...
Jasper R. R. Uijlings, Arnold W. M. Smeulders, Rem...
CIVR
2009
Springer
130views Image Analysis» more  CIVR 2009»
14 years 4 months ago
Exploring inter-concept relationship with context space for semantic video indexing
Semantic concept detectors are often individually and independently developed. Using peripherally related concepts for leveraging the power of joint detection, which is referred t...
Xiao-Yong Wei, Yu-Gang Jiang, Chong-Wah Ngo