Comparative analysis of hidden Markov models for multi-modal dialogue scene indexing

@article{Alatan2000ComparativeAO,
  title={Comparative analysis of hidden Markov models for multi-modal dialogue scene indexing},
  author={Aydin Alatan and A. Akansu and W. Wolf},
  journal={2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)},
  year={2000},
  volume={4},
  pages={2401-2404 vol.4}
}
  • Aydin Alatan, A. Akansu, W. Wolf
  • Published 2000
  • Computer Science
  • 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)
A class of audio-visual content is segmented into dialogue scenes using the state transitions of a novel hidden Markov model (HMM). Each shot is classified using both the audio track and the visual content to determine the state/scene transitions of the model. After simulations with circular and left-to-right HMM topologies, it is observed that both performing very well with multi-modal inputs. Moreover, for the circular topology, the comparisons between different training and observation sets… Expand
10 Citations

Figures, Tables, and Topics from this paper

Automatic multi-modal dialogue scene indexing
  • Aydin Alatan
  • Computer Science
  • Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205)
  • 2001
  • 6
Analysis and Extraction of Different DialogueScenes from Video Patterns
  • PDF
Retrieval of video story units by Markov entropy rate
  • 6
  • PDF
Audio-Assisted Movie Dialogue Detection
  • 12
  • Highly Influenced
  • PDF
A neural network approach to audio-assisted movie dialogue detection
  • 13
  • PDF
Movie Analysis with Emphasis to Dialogue and Action Scene Detection
  • 3
  • Highly Influenced
  • PDF
Pause concepts for audio segmentation at different semantic levels
  • 32
Film Mood and Its Quantitative Determinants in Different Types of Scenes
  • 3
  • PDF

References

SHOWING 1-10 OF 16 REFERENCES
Identification of story units in audio-visual sequences by joint audio and video processing
  • C. Saraceno, R. Leonardi
  • Computer Science
  • Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)
  • 1998
  • 63
Speaker dependent video indexing based on audio-visual interaction
  • S. Tsekeridou, I. Pitas
  • Computer Science
  • Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)
  • 1998
  • 12
Hidden Markov model parsing of video programs
  • W. Wolf
  • Computer Science
  • 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing
  • 1997
  • 60
  • PDF
A hidden Markov model framework for video segmentation using audio and image features
  • J. Boreczky, L. Wilcox
  • Computer Science
  • Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181)
  • 1998
  • 244
  • PDF
Integration of audio and visual information for content-based video segmentation
  • J. Huang, Z. Liu, Yao Wang
  • Computer Science
  • Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)
  • 1998
  • 91
Audio-visual content-based violent scene characterization
  • J. Nam, M. Alghoniemy, A. Tewfik
  • Computer Science
  • Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269)
  • 1998
  • 158
Video query: Research directions
  • 79
Identi cation of Story Units in Audio-Visual Sequences by Joint Audio and Video Processing,
  • Proceedings of ICIP'98,
  • 1998
Fundementals of Speech Recognition
  • Prentice Hall, Englewood Cli s, NJ, USA
  • 1993
Hidden Markov Model Framework for Video Segmentation
  • Audio and Image Features," in Proceedings of ICASSP'98,
  • 1998
...
1
2
...