Broadcast News Video Story Boundary Detection in TRECVID 2005/2006


Download TRECVID 2006 computed story boundaries
Download TRECVID 2005 computed story boundaries

Contacts : Winston Hsu, Lyndon Kennedy ,and Shih-Fu Chang

The TRECVID 2006 package contains the automatically detected story boundaries for the entire TRECVID 2006 test set (259 videos).

The TRECVID 2005 package contains the automatically detected story boundaries for the entire TRECVID 2005 test set (140 videos) and part of the development set (75 videos).

The detection algorithm utilizes the visual cue cluster construction (VC3) process based on the information bottleneck principle [1] and prosody features extracted from speech [2]. The approach emphasizes automatic discovery of salient features and effective classification via information theory measures. The technique was shown to be effective in the TRECVID 2004 story segmentation task.

To explore unique production styles in different channels, detection is conducted in a language-dependent fashion. Different detectors are trained separately for each language - English, Chinese, and Arabic.

The 2006 test set is different in that it includes videos captured in a time period long after the period for the training set, or from new channels not seen in 2005. This may cause potential degradation of the performance of the story boundary detector; however, due to the lack of annotations, we do not have performance evaluation of the story boundary detection over the 2006 data set. To partially address this issue, we have adopted an adaptive detection threshold so that the expected number of stories in each video is comparable with that seen in the same channel or language over the 2005 data set. Such adaptive scheme allows for an automatic unsupervised method for tuning the parameter of the detection method, without needing performance validation based on annotated data.

Please find more details in the README file along with the downloads (TV06, TV05).


[1] Winston H. Hsu and Shih-Fu Chang, "Visual Cue Cluster Construction via Information Bottleneck Principle and Kernel Density Estimation," The 4th International Conference on Image and Video Retrieval (CIVR), Singapore, July 20-22, 2005. (PDF)

[2] Winston H. Hsu, Lyndon Kennedy, Shih-Fu Chang, Martin Franz, and John Smith, "Columbia-IBM News Video Story Segmentation In TRECVID 2004," Columbia ADVENT Technical Report 209-2005-3, New York 2005.



For problems or questions regarding this web site contact The Web Master.
Last updated: Aug. 20, 2006.