Please use this identifier to cite or link to this item:
https://doi.org/10.1109/MMMC.2005.63
Title: | Retrieval of news video using video sequence matching | Authors: | Kim, Y.-T. Chua, T.-S. |
Keywords: | Longest common sub-sequence Sequence matching Similarity measure Video retrieval |
Issue Date: | 2005 | Citation: | Kim, Y.-T.,Chua, T.-S. (2005). Retrieval of news video using video sequence matching. Proceedings of the 11th International Multimedia Modelling Conference, MMM 2005 : 68-75. ScholarBank@NUS Repository. https://doi.org/10.1109/MMMC.2005.63 | Abstract: | In this paper, we propose a new algorithm to find video clips with different temporal durations and some spatial variations. We adopt a longest common sub-sequence (LCS) matching technique for measuring the temporal similarity between video clips. Based on the measure we propose 3 techniques to improve the retrieval effectiveness. First, we use a few coefficients in the low frequency region of DCT block as the basis to represent spatial features. Second, we heuristically determine a suitable quantization step-size for visual features to better tolerate spatial variations of similar video clips and propose a paired quantizer method. Third, we incorporate the compactness and/or continuity of matched common sub-sequences in the LCS measure to better reflect temporal characteristics of video. The performance of the proposed algorithm shows an improvement of 63.5% in terms of MAP (mean average precision) as compared to an existing algorithm. The results show that our approach is effective for news video retrieval. © 2005 IEEE. | Source Title: | Proceedings of the 11th International Multimedia Modelling Conference, MMM 2005 | URI: | http://scholarbank.nus.edu.sg/handle/10635/78324 | ISBN: | 0769521649 | DOI: | 10.1109/MMMC.2005.63 |
Appears in Collections: | Staff Publications |
Show full item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.