DocumentCode :
2290343
Title :
Domain adaptive semantic diffusion for large scale context-based video annotation
Author :
Jiang, Yu-Gang ; Wang, Jun ; Chang, Shih-Fu ; Ngo, Chong-Wah
Author_Institution :
Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
fYear :
2009
fDate :
Sept. 29 2009-Oct. 2 2009
Firstpage :
1420
Lastpage :
1427
Abstract :
Learning to cope with domain change has been known as a challenging problem in many real-world applications. This paper proposes a novel and efficient approach, named domain adaptive semantic diffusion (DASD), to exploit semantic context while considering the domain-shift-of-context for large scale video concept annotation. Starting with a large set of concept detectors, the proposed DASD refines the initial annotation results using graph diffusion technique, which preserves the consistency and smoothness of the annotation over a semantic graph. Different from the existing graph learning methods which capture relations among data samples, the semantic graph treats concepts as nodes and the concept affinities as the weights of edges. Particularly, the DASD approach is capable of simultaneously improving the annotation results and adapting the concept affinities to new test data. The adaptation provides a means to handle domain change between training and test data, which occurs very often in video annotation task. We conduct extensive experiments to improve annotation results of 374 concepts over 340 hours of videos from TRECVID 2005-2007 data sets. Results show consistent and significant performance gain over various baselines. In addition, the proposed approach is very efficient, completing DASD over 374 concepts within just 2 milliseconds for each video shot on a regular PC.
Keywords :
graph theory; object detection; task analysis; video signal processing; domain adaptive semantic diffusion; graph diffusion technique; graph learning methods; large scale context-based video concept annotation; semantic graph; Airplanes; Application software; Computer science; Computer vision; Detectors; Gunshot detection systems; Large-scale systems; Testing; Training data; Videoconference;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision, 2009 IEEE 12th International Conference on
Conference_Location :
Kyoto
ISSN :
1550-5499
Print_ISBN :
978-1-4244-4420-5
Electronic_ISBN :
1550-5499
Type :
conf
DOI :
10.1109/ICCV.2009.5459295
Filename :
5459295
Link To Document :
بازگشت