Boundary Error Analysis and Categorization in the TRECVID News Story Segmentation Task
In this paper, an error analysis based on boundary error popularity (frequency) including semantic boundary categorization is applied in the context of the news story segmentation task from TRECVID. Clusters of systems were defined based on the input resources they used including video, audio and automatic speech recognition. A cross-popularity specific index was used to measure boundary error popularity across clusters, which allowed goal-driven selection of boundaries to be categorized. A wide set of boundaries was viewed and a summary of the error types is presented. This framework allowed conclusions about the behavior of resource-based clusters in the context of news story segmentation.
KeywordsFalse Alarm Boundary Error Automatic Speech Recognition Test Collection Input Resource
Unable to display preview. Download preview PDF.
- 1.Hsu, W.H.-M., Chang, S.-F.: Generative,Discriminative, and Ensemble Learning on Multi-modal Perceptual Fusion toward News Video Story Segmentation. In: IEEE International Conference on Multimedia and Expo (2004)Google Scholar
- 2.Chua, T.S., Chang, S.F., Chaisrn, L., Hsu, W.: Story Boundary Detection in Large Broadcast News Video Archives - Techniques, Experience and Trends. In: Proceedings of the 12th annual ACM conference on Multimedia (MM 2004), pp. 656–659 (2004)Google Scholar
- 3.Kraaij, W., Smeaton, A.F., Over, P., Arlandis, J.: TRECVID 2004 - An Overview. TREC Video Retrieval Evaluation Online Proceedings (2003), http://www-nlpir.nist.gov/projects/trecvid/tv.pubs.org.html
- 4.Wayne, C.: Multilingual Topic Detection and Tracking: Successful Research Enabled by Corpora and Evaluation. In: Language Resources and Evaluation Conference (LREC), pp. 1487–1494 (2000)Google Scholar
- 6.Voorhees, E.M., Harman, D.K.: Common Evaluation Measures. Proceedings of the Tenth Text Retrieval Conference (TREC) A-14, http://trec.nist.gov/pubs/trec10