Automated Metadata in Multimedia Information Systems: Creation, Refinement, Use in Surrogates, and Evaluation (repost)

Improvements in network bandwidth along with dramatic drops in digital storage and processing costs have resulted in the explosive growth of multimedia (combinations of text, image, audio, and video) resources on the Internet and in digital repositories. A suite of computer technologies delivering speech, image, and natural language understanding can automatically derive descriptive metadata for such resources.