QuickTopic free message boards logo
Skip to Messages

TOPIC:

Video Google / Object Level Grouping for Video Shots

9
Ekksujhr
07-14-2009
09:32 PM ET (US)
ol8Dsa
8
pplivee
09-18-2008
03:20 PM ET (US)
www.7974.cn
www.1987i.com
www.xucui.com
seo
7
pplivee
09-18-2008
03:20 PM ET (US)
www.0739ren.com
club.001uc.com
club.001uc.com/bbs
www.0739ren.com
  Messages 6-5 deleted by author 09-19-2008 02:28 AM
4
pasdelbas
08-17-2008
12:12 PM ET (US)
bocsitboals
3
Deleted by topic administrator 05-17-2008 10:16 AM
2
Anup Doshi
10-20-2005
02:39 PM ET (US)
Is there any measure of how well the object level grouping algorithm works (precision-recall, etc.)? I would particularly be interested to see if it comes up with any false positives, and what those might look like. They seem to be able to detect the van and Bill Murray (Figs 10+11) very well. It seems like they might be able to find Bill if we threw in some frames from Ghostbusters as well. Also did they mention how long any of this takes?
1
Brendan Morris
10-20-2005
01:17 PM ET (US)
Very interesting. This seems to work quite well in the examples presented. They mention that the "words" trained from Run Lola Run where also used satisfactorily on Groundhog Day, but I'm not sure how this can be. This seems to be more of a single coherent video method at the moment. My main questions have to do with the conversion to text retrival as I'm not familiar with this at all. The conversion from object frequencies to a suitable search vector is lost on me.

Print | RSS Views: 2393 (Unique: 1123 ) / Subscribers: 0 | What's this?