News video story segmentation using fusion of multi-level multi-modal features in TRECVID 2003

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 3, Issue , 2004, Pages

  Hsu, W ^a   Kennedy, L ^a   Huang, C W ^a   Chang, S F ^a   Lin, C Y ^b   Iyengar, G ^b  

^a Columbia University ^*  (United States)

^b IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

AUTOMATIC SPEECH RECOGNITION (ASR); DATA LABELING; MAXIMUM ENTROPY (ME); NEWS STORY SEGMENTATION;

ENTROPY; FUZZY SETS; MARKOV PROCESSES; MATHEMATICAL MODELS; PARAMETER ESTIMATION; SPEECH RECOGNITION; STATISTICAL METHODS;

IMAGE SEGMENTATION;

EID: 4544242800     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. W. Hsu and S.-F. Chang, "A statistical framework for fusing mid-level perceptual features in news story segmentation," in IEEE International Conference on Multimedia and Expo, 2003.
2. W. Hsu, S.-F. Chang, C.-W. Huang, L. Kennedy, C.-Y. Lin, and G. Iyengar, "Discovery and fusion of salient multi-modal features towards news story segmentation," in SPIE/Electronic Imaging, San Jose, CA, Jan. 2004.
3. D. Beeferman, A. Berger, and J. Lafferty, "Statistical models for text segmentation," Machine Learning, vol. 34, no. special issue on Natural Language Learning, pp. 177-210, 1999.
4. J. Vaissiere, "Language-independent prosodic features," in Prosody: Models and Measurements, Anne Cutler and D. Robert Ladd, Eds., pp. 53-66. Springer, Berlin, 1983.
5. E. Shriberg, A. Stolcke, D. Hakkani-Tur, and G. Tur, "Prosody-based automatic segmentation of speech into sentences and topics," Speech Communication, vol. 32, pp. 127-154, 2000.
6. H. Sundaram, Segmentation, Structure Detection and Summarization of Multimedia Sequences, Ph.D. thesis, Columbia University, 2002.
7. M. Franz, J. S. McCarley, S. Roukos, T. Ward, and W.-J. Zhu, "Segmentation and detection at ibm: Hybrid statistical models and two-tiered clustering broadcast news domain," in Proceedings of TDT-3 Workshop, 2000.