Layered Dynamic Mixture Model for Pattern Discovery in Asynchronous Multi-Modal Streams
| Citation: |
* Xie, L.; Kennedy, L.; Chang, S-F; Divakaaran, A.; Sun, H.; Lin, C-Y, "Layered Dynamic Mixture Model for Pattern Discovery in Asynchronous Multi-Modal Streams", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ISSN: 1520-6149, Vol. 2, pp. 1053-1056, March 2005 (IEEE Xplore) |
| MERL Report: | TR2005-078 |
We propose a layered dynamic mixture model for asynchronous multi-modal fusion for unsupervised pattern discovery in video. The lower layer of the model uses generative temporal structures such as a hierarchical hidden Markov model to convert the audio-visual streams into mid-level labels, it also models the correlations in text with probabilistic latent semantic analysis. The upper layer fuses the statistical evidence across diverse modalities with a flexible meta-mixture model that assumes loose temporal correspondence. Evaluation on a large news database shows that multi-modal clusters have better correspondence to news topics than audio-visual clusters alone; novel analysis techniques suggest that meaningful clusters occur when the prediction of salient features by the model concurs with those shown in the story clusters.
