Title :
A Fast and Accurate Video Semantic-Indexing System Using Fast MAP Adaptation and GMM Supervectors
Author :
Inoue, Nakamasa ; Shinoda, Koichi
Author_Institution :
Dept. of Comput. Sci., Tokyo Inst. of Technol., Tokyo, Japan
Abstract :
We propose a fast maximum a posteriori (MAP) adaptation method for video semantic indexing that uses Gaussian mixture model (GMM) supervectors. In this method, a tree-structured GMM is utilzed to decrease the computational cost, where only the output probabilities of mixture components close to an input sample are precisely calculated. Experimental evaluation on the TRECVID 2010 dataset demonstrates the effectiveness of the proposed method. The calculation time of the MAP adaptation step is reduced by 76.2% compared with that of a conventional method. The total calculation time is reduced by 56.6% while keeping the same level of the accuracy.
Keywords :
Gaussian processes; indexing; maximum likelihood estimation; trees (mathematics); video signal processing; GMM supervectors; Gaussian mixture model supervectors; TRECVID 2010 dataset; fast MAP adaptation; fast maximum a posteriori adaptation method; output probabilities; video semantic-indexing system; Accuracy; Feature extraction; Image color analysis; Indexing; Kernel; Semantics; Support vector machines; Gaussian mixture model (GMM) supervectors; maximum a posteriori (MAP) adaptation; video semantic indexing;
Journal_Title :
Multimedia, IEEE Transactions on
DOI :
10.1109/TMM.2012.2191395