Enhanced Semi-Supervised Learning for Automatic Video Annotation

Meng Wang, Xian-Sheng Hua, Li-Rong Dai, Yan Song

Abstract

For automatic semantic annotation of large-scale video database, the insufficiency of labeled training samples is a major obstacle. General semi-supervised learning algorithms can help solve the problem but the improvement is limited. In this paper, two semi-supervised learning algorithms, self-training and co-training, are enhanced by exploring the temporal consistency of semantic concepts in video sequences. In the enhanced algorithms, instead of individual shots, time-constraint shot clusters are taken as the basic sample units, in which most mis-classifications can be corrected before they are applied for re-training, thus more accurate statistical models can be obtained. Experiments show that enhanced self-training/co-training significantly improves the performance of video annotation
BibTeX
@inproceedings{wang2006enhanced,
  author = {Meng Wang and Xian-Sheng Hua and Li-Rong Dai and Yan Song},
  title = {{Enhanced Semi-Supervised Learning for Automatic Video Annotation}},
  booktitle = {ICME},
  year = {2006},
  doi = {10.1109/icme.2006.262823},
}

Loading related content...

Figure