         News Video Story Boundary Detection in TRECVID 2005
======================================================================
	  Winston Hsu, Lyndon Kennedy, and Shih-Fu Chang
	
		Columbia University, New York
		
			- 09/08/2005 - 
	
::Download Site::
http://www.ee.columbia.edu/dvmm/downloads/cuex_story.htm


::Contact::
Winston Hsu <winston@ee.columbia.edu>
Shih-Fu Chang <sfchang@ee.columbia.edu>


::Description::
This 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 remaining 75 videos in the development set has been used for training 
and testing in a 5-fold cross-validation set up. The detection performance, 
based on the F1 measure used in prior story detection evaluation, for each 
language is listed below.

Lang.	F1
-------------
ARB	0.821 
CHN	0.840
ENG	0.451


The ENG channel in the development set is troubled by the special reports 
such as US presidential election and Peterson's case (e.g., 
TRECVID2005_252). We expect the performance figure to be significantly 
improved if such special reports segments are not present.


::Data Format::
Boundary files are separated in development (.\devel) and test (.\test) 
sets. The boundary files are in *.bdr. The language categorization of each 
video is listed in "SS_{devel/test}05_{ARB/CHN/ENG}.txt".

Each boundary file is represented with two columns: the first is the 
starting point (in second) of the boundary and the second is reserved for 
story (1) and non-story (0) classification of each story segment. A "-1" 
value is assigned now since story vs. non-story classification is not 
performed in this release.


::References::
[1] Winston Hsu and Shih-Fu Chang, "Visual Cue Cluster Construction via 
Information Bottleneck Principle and Kernel Density Estimation," In 
International Conference on Content-Based Image and Video Retrieval (CIVR), 
Singapore, 2005. 

[2] Winston Hsu, Lyndon Kennedy, Shih-Fu Chang, Martin Franz, and 
John R. Smith, "COLUMBIA-IBM NEWS VIDEO STORY SEGMENTATION IN TRECVID 
2004," ADVENT Technical Report #207-2005-3 Columbia Universiry, 2005.


