TY - GEN
T1 - Co-clustering of time-evolving news story with transcript and keyframe
AU - Wu, Xiao
AU - Ngo, Chong Wah
AU - Li, Qing
PY - 2005/12/1
Y1 - 2005/12/1
N2 - This paper presents techniques in clustering the sametopic news stories according to event themes. We model the relationship of stories with textual and visual concepts under the representation of bipartite graph. The textual and visual concepts are extracted respectively from speech transcripts and keyframes. Co-clustering algorithm is employed to exploit the duality of stories and textual-visual concepts based on spectral graph partitioning. Experimental results on TRECVID-2004 corpus show that the co-clustering of news stories with textual-visual concepts is significantly better than the co-clustering with either textual or visual concept alone.
AB - This paper presents techniques in clustering the sametopic news stories according to event themes. We model the relationship of stories with textual and visual concepts under the representation of bipartite graph. The textual and visual concepts are extracted respectively from speech transcripts and keyframes. Co-clustering algorithm is employed to exploit the duality of stories and textual-visual concepts based on spectral graph partitioning. Experimental results on TRECVID-2004 corpus show that the co-clustering of news stories with textual-visual concepts is significantly better than the co-clustering with either textual or visual concept alone.
UR - http://www.scopus.com/inward/record.url?scp=33750539707&partnerID=8YFLogxK
U2 - 10.1109/ICME.2005.1521374
DO - 10.1109/ICME.2005.1521374
M3 - Conference article published in proceeding or book
AN - SCOPUS:33750539707
SN - 0780393325
SN - 9780780393325
T3 - IEEE International Conference on Multimedia and Expo, ICME 2005
SP - 117
EP - 120
BT - IEEE International Conference on Multimedia and Expo, ICME 2005
T2 - IEEE International Conference on Multimedia and Expo, ICME 2005
Y2 - 6 July 2005 through 8 July 2005
ER -