6553 search results - page 928 / 1311 » Face modeling for recognition |
182
click to vote
MCS
2005
Springer
16 years 10 days ago
2005
Springer
A Half-Against-Half (HAH) multi-class SVM is proposed in this paper. Unlike the commonly used One-Against-All (OVA) and One-Against-One (OVO) implementation methods, HAH is built ...
216
click to vote
IJPRAI
2008
15 years 6 months ago
2008
We present a shape based method for automatic people detection and counting without any assumption or knowledge of camera motion. The proposed method is applied to athletic videos...
182
Voted
JALC
2007
15 years 6 months ago
2007
The basic finite automata model has been extended over the years with different acceptance modes (nondeterminism, alternation), new or improved devices (two-way heads, pebbles, ...
162
click to vote
NAACL
2010
15 years 4 months ago
2010
In a Wizard-of-Oz experiment with multiple wizard subjects, each wizard viewed automated speech recognition (ASR) results for utterances whose interpretation is critical to task s...
227
click to vote
ICIAP
2009
ACM
15 years 4 months ago
2009
ACM
Abstract. The recognition of events in videos is a relevant and challenging task of automatic semantic video analysis. At present one of the most successful frameworks, used for ob...