DocumentCode :
2501709
Title :
Active inference for retrieval in camera networks
Author :
Chen, Daozheng ; Bilgic, Mustafa ; Getoor, Lise ; Jacobs, David ; Mihalkova, Lilyana ; Yeh, Tom
Author_Institution :
Dept. of Comput. Sci., Univ. of Maryland, College Park, MD, USA
fYear :
2011
fDate :
7-7 Jan. 2011
Firstpage :
13
Lastpage :
20
Abstract :
We address the problem of searching camera network videos to retrieve frames containing specified individuals. We show the benefit of utilizing a learned probabilistic model that captures dependencies among the cameras. In addition, we develop an active inference framework that can request human input at inference time, directing human attention to the portions of the videos whose correct annotation would provide the biggest performance improvements. Our primary contribution is to show that by mapping video frames in a camera network onto a graphical model, we can apply collective classification and active inference algorithms to significantly increase the performance of the retrieval system, while minimizing the number of human annotations required.
Keywords :
cameras; inference mechanisms; probability; search problems; video retrieval; video signal processing; active inference; camera network; graphical model; human annotation; probabilistic model; retrieval system; searching problem; video frame; Cameras; Humans; Inference algorithms; Probabilistic logic; Training; Training data; Videos;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Person-Oriented Vision (POV), 2011 IEEE Workshop on
Conference_Location :
Kona, HI
Print_ISBN :
978-1-61284-036-9
Type :
conf
DOI :
10.1109/POV.2011.5712363
Filename :
5712363
Link To Document :
بازگشت