11 search results - page 2 / 3 » 3WNews: who, where, and when in news video |
IEEEMM
2000
13 years 5 months ago
2000
reness has more abstract social value: People who use frequent eye contact are perceived as more attentive, friendly, cooperative, confident, mature, and sincere than those who avo...
MM
2010
ACM
13 years 5 months ago
2010
ACM
This paper proposes an approach for the automatic recognition of roles in settings like news and talk-shows, where roles correspond to specific functions like Anchorman, Guest or ...
KDD
2006
ACM
14 years 5 months ago
2006
ACM
The primary purpose of news articles is to convey information about who, what, when and where. But learning and summarizing these relationships for collections of thousands to mil...
ICASSP
2009
IEEE
13 years 12 months ago
2009
IEEE
Speaker diarization is originally defined as the task of determining “who spoke when” given an audio track and no other prior knowledge of any kind. The following article sho...
CHI
2005
ACM
14 years 5 months ago
2005
ACM
Experiments were conducted to investigate the interdependency of frame rates (30, 15, 10 fps) and audiovisual skew (from +163 to -233 ms1 ). Noised nonsense words like 'abaga...