Repository hosted by TU Delft Library

Home · Contact · About · Disclaimer ·

Boundary error analysis and categorization in the TRECVID news story segmentation task

Publication files not online:

Author: Arlandis, J. · Over, P. · Kraaij, W.
Publisher: Springer
Place: Berlin
Institution: TNO Industrie en Techniek
Source:Leow, W.K.Lew, M.S.Chua, T.S.Ma, W.Y.Chaisorn, L., 4th International Conference on Image and Video Retrieval, CIVR 2005, 20-22 July 2005, Singapore, 103-112
Lecture Notes in Computer Science - LNCS
Identifier: 238763
Keywords: Informatics · Error analysis · Semantics · Speech recognition · Automatic speech recognition · Boundary error analysis · News story segmentation · Resource-based clusters · Image segmentation


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 TRECVTD1. 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. © Springer-Verlag Berlin Heidelberg 2005.