27 October 2013 The study on the feedback of large scale content-based video retrieval
Author Affiliations +
Proceedings Volume 8919, MIPPR 2013: Pattern Recognition and Computer Vision; 891904 (2013) https://doi.org/10.1117/12.2032063
Event: Eighth International Symposium on Multispectral Image Processing and Pattern Recognition, 2013, Wuhan, China
Abstract
This paper addresses the problem of large scale content-based video retrieval with relevance feedback. We analyze the common methods which leverage local feature detectors to extract feature descriptors from video collections and perform multi-level matching after indexing and retrieval of feature vectors. Instead of learning similarity-preserving codes, an approach of relevance feedback in a light-weight way is proposed. A relevance model is proposed to merge semantic similarity with the original distance matching at descriptor level. By learning several weights using canonical correlation analysis (CCA), the resulting candidate list of similar videos changes according to relevance feedback. Finally, we demonstrate the improvement of the proposed method by experiments on a standard real world dataset.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xiang-dong Qi, Xiang-dong Qi, Da-wei Liu, Da-wei Liu, Jin-lin Wang, Jin-lin Wang, } "The study on the feedback of large scale content-based video retrieval", Proc. SPIE 8919, MIPPR 2013: Pattern Recognition and Computer Vision, 891904 (27 October 2013); doi: 10.1117/12.2032063; https://doi.org/10.1117/12.2032063
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT

Developing power tools for video indexing and retrieval
Proceedings of SPIE (April 01 1994)
Activity-based exploitation of Full Motion Video (FMV)
Proceedings of SPIE (May 25 2012)
Detecting sky and vegetation in outdoor images
Proceedings of SPIE (December 23 1999)
Content based image and video retrieval
Proceedings of SPIE (February 26 2010)
Automatic annotation of image and video using semantics
Proceedings of SPIE (February 26 2010)

Back to Top