Multi-Modal Video Concept Extraction Using Co-Training

For large scale automatic semantic video characterization, it is necessary to learn and model a large number of semantic concepts. A major obstacle to this is the insufficiency of labeled training samples. Semi-supervised learning algorithms such as cotraining may help by incorporating a large amount of unlabeled data, which allows the redundant information across views to improve the learning performance. Although co-training has been successfully applied in several domains, it has not been used to detect video concepts before. In this paper, we extend co-training to the domain of video concept detection and investigate different strategies of co-training as well as their effects to the detection accuracy. We demonstrate performance based on the guideline of the TRECVID’03 semantic concept extraction task.

• Type: Conference
• Year: 2005
• Where: ICMCS
• Authors: Rong Yan, Milind R. Naphade
• Keywords: Automatic Semantic Video, Co-training, ICMCS 2005, Semantic Concept