Semi-supervised Learning Methods for Data Labeling

The explosive growth of video sources has created new challenges for the research community. Many applications in computer vision and multimedia retrieval, such as visual information retrieval, object recognition, and human activity modeling, require labeling/annotating of video data. Manually labeling video data, however, is not only a labor intensive and time-consuming task, but also subject to human errors. We have been developing technologies to address the problem using semi-supervised learning methods.

Related Publications:

• W. Wu, J. Yang, Semi-Automatically Labeling Objects in Images, IEEE Transaction on Image Processing, vol.18, No. 6, pp. 1340-1349, 2009.

• H. Cheng, Z. Liu, J. Yang, Sparsity Induced Similarity Measure for Label Propagation, Proceedings of IEEE International Conference on Computer Vision (ICCV), 2009.

• W. Wu and J. Yang, Semi-Supervised Learning of Object Categories from Paired Local Features, Proceedings of ACM International Conference on Image and Video Retrieval (CIVR 2008).

• R. Yan, J. Zhang, J. Yang, and A. Hauptmann, A Discriminative Learning Framework with Pairwise Constraints for Video Object Classification, IEEE Transaction on Pattern Analysis and Machine Intelligence (PAMI), Vol 28, No.4, pp.578-593, 2006.

• W. Wu, J. Yang, SmartLabel: An Object Labeling Tool Using Iterated Harmonic Energy Minimization, Proceedings of the 14th ACM international conference on Multimedia(MM), pp. 891-900, 2006.

• W. Wu, D. Chen and J. Yang, Integrating Co-Training and Recognition for Text Detection, Proceedings of IEEE International Conference on Multimedia & Expo 2005 (ICME 2005), pp. 1166 - 1169, 2005.

• R. Yan, J. Zhang, J. Yang and A. Hauptmann, A Discriminative Learning Framework with Pairwise Constraints for Video Object Classification, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Vol. 2 , pp. 284-291, 2004.

• R. Yan, J. Yang, A. Hauptmann, Automatically Labeling Video Data Using Multi-class Active Learning, Proceedings of Internation Conference on Computer Vision (ICCV) 2003, pp. 516 - 523, 2003.

Back to the previous page