Title :
A hierarchical approach to story segmentation of large broadcast news video corpus
Author :
Chaisorn, Lekha ; Chua, Tat-Seng ; Lee, Chin-Hui ; Tian, Qi
Author_Institution :
Sch. of Comput., Nat. Univ. of Singapore
Abstract :
A multi-modal two-level framework for news story segmentation was proposed in Chaisorn et al. (2002). This paper presents our extended work scaled to cope with a large news video corpus used in TRECVID 2003 evaluation. We divided our system into two levels: the shot level that classifies input video shots into one of the predefined categories using a hybrid of heuristic and learning based approaches; and story level that performs story segmentation using the HMM framework based on the output of shot level and other temporal features. A heuristic rule-based technique is then employed to classify each detected story into "news" or "miscellaneous". We evaluated our system on over 120 hours of news video and showed that our system could achieve an accuracy of more than 77%. Our system came first in the TRECVID 2003 story segmentation task
Keywords :
content-based retrieval; database indexing; heuristic programming; hidden Markov models; knowledge based systems; very large databases; video databases; HMM framework; TRECVID 2003 evaluation; broadcast news video corpus; heuristic rule-based technique; hierarchical story segmentation; input video shots; large video corpus; learning based approach; miscellaneous classification; multi-modal two-level framework; news classification; news story segmentation; shot level output; Broadcast technology; Broadcasting; Data mining; Feature extraction; Guidelines; Gunshot detection systems; Hidden Markov models; Information retrieval; Multimedia communication; Performance analysis;
Conference_Titel :
Multimedia and Expo, 2004. ICME '04. 2004 IEEE International Conference on
Conference_Location :
Taipei
Print_ISBN :
0-7803-8603-5
DOI :
10.1109/ICME.2004.1394401
