Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | SS-12.5 |
| Session: | Information Fusion for Multimedia Annotation and Retrieval |
| Time: | Friday, May 21, 14:08 - 14:25 |
| Presentation: |
Special Session Lecture |
| Topic: |
Special Sessions: Information Fusion for Multimedia Annotation and Retrieval |
| Title: |
STATISTICAL MODELS FOR AUTOMATIC VIDEO ANNOTATION AND RETRIEVAL |
| Authors: |
V. Lavrenko; University of Massachusetts | | |
| | S. L. Feng; University of Massachusetts | | |
| | R. Manmatha; University of Massachusetts | | |
| Abstract: |
We apply a continuous relevance model (CRM) to the problem of directly retrieving the visual content of videos using text queries. The model computes a joint probability model for image features and words using a training set of annotated images. The model may then be used to annotate unseen test images. The probabilistic annotations are used for retrieval using text queries. We also propose a modified model - the normalized CRM - which substantially improves performance on a subset of the TREC Video dataset. |
| |
| Back | |