Adaptive Learning for Celebrity Identification With Video Context
- 10 April 2014
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 16 (5) , 1473-1485
Abstract
In this paper, we propose a novel semi-supervised learning strategy to address the problem of celebrity identification. The video context information is explored to facilitate the learning process based on the assumption that faces in the same video track share the same identity. Once a frame within a track is recognized confidently, the label can be propagated through the whole track, referred to as the confident track. More specifically, given a few static images and vast face videos, an initial weak classifier is trained and gradually evolves by iteratively promoting the confident tracks into the “labeled” set. The iterative selection process enriches the diversity of the “labeled” set such that the performance of the classifier is gradually improved. This learning theme may suffer from semantic drifting caused by errors in selecting the confident tracks. To address this issue, we propose to treat the selected frames as related samples-an intermediate state between labeled and unlabeled instead of labeled as in the traditional approach. To evaluate the performance, we construct a new dataset, which includes 3000 static images and 2700 face tracks of 30 celebrities. Comprehensive evaluations on this dataset and a public video dataset indicate significant improvement of our approach over established baseline methods.Keywords
This publication has 28 references indexed in Scilit:
- Segmentation Propagation in ImageNet2012
- Combining Self Training and Active Learning for Video Segmentation2011
- Multi-view Laplacian Support Vector Machines2011
- Robust Multi-View Boosting with Priors2010
- Semantic annotation of soccer videos by visual instance clustering and spatial/temporal reasoning in ontologiesMultimedia Tools and Applications, 2009
- A Network of Coupled Chaotic Maps for Adaptive Multi-Scale Image SegmentationInternational Journal of Neural Systems, 2003
- Multiresolution gray-scale and rotation invariant texture classification with local binary patternsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- A Generalized Representer Theorem2001
- Name-It: naming and detecting faces in news videosIEEE MultiMedia, 1999
- Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filtersJournal of the Optical Society of America A, 1985