Combining Multi-Modal Features for News Story Correlation Analysis

Abstract:

How to combine multi-modal features effectively is a difficult problem in news story correlation analysis, this paper puts forward a new two-stage fusion approach based on visual and textual features fusion to solve this problem. First we use a co-clustering method to get the clustering groups of similar stories with the visual and semantic information of news story. And then, on the base of the result of the first step, we use different weighted strategies to analyze the news story correlation in a further way, which aim at the different type of news story. The methods can get a better result of the news story correlation analysis by experiments.

• Periodical: Advanced Materials Research (Volumes 268-270)
• Pages: 1040-1045
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.268-270.1040
• Online since: July 2011
• Authors: Dan Wen Chen, Li Qiong Deng, Zhi Min Yuan, Ling Da Wu
• Keywords: Multi-Modal Features, News Story Correlation Analysis, Two-Stage Fusion

References

[1] Jun Wen，Ling-da Wu，Pu Zeng，et al．Tracking Cross-Lingual News Stories with Efficient Near Duplicate Detection．Journal of Information & Computational Science, 5(3): 1387-1395(2008).

[2] Ide I, Mo H, Katayama N, et al. Topic threading for structuring a large-scale news video archive[C]. Image and Video Retrieval: Third International Conference. Dublin, Ireland: 123-131(2004).

DOI: 10.1007/978-3-540-27814-6_18

[3] Ide I, Mo H, Katayama N, et al. Exploiting topic thread structures in a news video archive for the semi-automatic generation of video summaries[C]. 2006 IEEE International Conference on Multimedia and Expo. Toronto, Canada: 1473-1476(2006).

DOI: 10.1109/icme.2006.262820

[4] Wu Xiao, Zhao Wan-lei, Ngo C-W. Near-duplicate keyframe retrieval with visual keywords and semantic context[C]. Proceedings of the 6th ACM international conference on Image and video retrieval. Amsterdam, The Netherlands: 162-169(2007).

DOI: 10.1145/1282280.1282309

[5] Jiang Yu-gang, Wei Xiaoyong, Ngo C-W, et al. Modeling local interest points for semantic detection and video search at TRECVID 2006[C]. Proceeding of TRECVID Workshop 2006. Gaithersburg, USA(2006).

[6] Zhai Y, Shah M. Tracking news stories across different sources[C]. Proceeding of the 13th Annual ACM International Conference on Multimedia. Singapore: 2-10(2005).

DOI: 10.1145/1101149.1101152

[7] Kender J R, Naphade M R. Visual concepts for news story tracking: analyzing and exploiting the NIST Trecvid video annotation experiment[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA(2005).

DOI: 10.1109/cvpr.2005.371

[8] D.G. Lowe. Distinctive image features from scale invariant keypoints. International Journal of Computer Vision, 60(2): 90-110(2006).

DOI: 10.1023/b:visi.0000029664.99615.94

[9] Han Bing. Research on News Video Story Correlation Analysis. Master Thesis. November (2010).

[10] X. Wu, C. W. Ngo, Q. Li. Co-clustering of time-evolving story with transcript and keyframe, in Proc. Int. Conf. Multimedia and Expo, pp: 117-120(2005).

DOI: 10.1109/icme.2005.1521374

[11] Xiao Wu，Chong-Wah Ngo and Qing Li. Threading and Autodocumenting News Videos. IEEE SIGNAL PROCESSING MAGAZING. pp: 59-68(2006).

DOI: 10.1109/msp.2006.1621449