Please use this identifier to cite or link to this item: https://doi.org/10.1145/1870121.1870125
Title: Near-duplicate keyframe retrieval by semi-supervised learning and Nonrigid image matching
Authors: Zhu, J.
Hoi, S.C.H.
Lyu, M.R.
Yan, S. 
Keywords: Image copy detection
Near-duplicate keyframe
Nonrigid Image Matching
Semi-supervised learning
Issue Date: Jan-2011
Source: Zhu, J., Hoi, S.C.H., Lyu, M.R., Yan, S. (2011-01). Near-duplicate keyframe retrieval by semi-supervised learning and Nonrigid image matching. ACM Transactions on Multimedia Computing, Communications and Applications 7 (1) : -. ScholarBank@NUS Repository. https://doi.org/10.1145/1870121.1870125
Abstract: Near-duplicate keyframe (NDK) retrieval techniques are critical to many real-world multimedia applications. Over the last few years, we have witnessed a surge of attention on studying near-duplicate image/keyframe retrieval in the multimedia community. To facilitate an effective approach to NDK retrieval on large-scale data, we suggest an effective Multi-Level Ranking (MLR) scheme that effectively retrieves NDKs in a coarse-to-fine manner. One key stage of the MLR ranking scheme is how to learn an effective ranking function with extremely small training examples in a near-duplicate detection task. To attack this challenge, we employ a semi-supervised learning method, semi-supervised support vector machines, which is able to significantly improve the retrieval performance by exploiting unlabeled data. Another key stage of the MLR scheme is to perform a fine matching among a subset of keyframe candidates retrieved from the previous coarse ranking stage. In contrast to previous approaches based on either simple heuristics or rigid matching models, we propose a novel Nonrigid Image Matching (NIM) approach to tackle near-duplicate keyframe retrieval from real-world video corpora in order to conduct an effective fine matching. Compared with the conventional methods, the proposed NIM approach can recover explicit mapping between two near-duplicate images with a few deformation parameters and find out the correct correspondences from noisy data simultaneously. To evaluate the effectiveness of our proposed approach, we performed extensive experiments on two benchmark testbeds extracted from the TRECVID2003 and TRECVID2004 corpora. The promising results indicate that our proposed method is more effective than other state-of-the-art approaches for near-duplicate keyframe retrieval.© 2011 ACM.
Source Title: ACM Transactions on Multimedia Computing, Communications and Applications
URI: http://scholarbank.nus.edu.sg/handle/10635/56771
ISSN: 15516857
DOI: 10.1145/1870121.1870125
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

13
checked on Dec 5, 2017

WEB OF SCIENCETM
Citations

1
checked on Dec 5, 2017

Page view(s)

23
checked on Dec 11, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.