A review is given on recent advances in using audio and visual information jointly for accomplishing multimedia content analysis. Audio and visual features that can effectively characterize scene content are described, and selected algorithms for segmentation and classification are reviewed. Further, audio and visual descriptors and description schemes that are being considered by the MPEG-7 standard for multimedia content description are highlighted.
ASJC Scopus subject areas
- Signal Processing
- Electrical and Electronic Engineering
- Applied Mathematics