Name
Abstract | ||
|---|---|---|
Visual object tracking can be considered as an online procedure to adaptively measure the foreground object similarity itself. However, many previous works usually adopt a fixed metric or offline metric learning to evaluate this dynamic process; even with some online metric learning (OML) trackers, their models often suffer from overfitting issues. To overcome these deficiencies, we propose a self-supervised tracking method that incorporates adaptive metric learning and semisupervised learning into a unified framework. For similarity measurement, we design a new OML model via low-rank constraint to handle overfitting. In particular, we employ the max norm instead of the trace norm used in our previous work. This not only maintains the low-rank property to overcome overfitting, but also reduces the computational complexity from to , such that the new model is more suitable for object tracking. Moreover, by associating the information from stored training templates with unlabeled testing samples, a bilinear graph is defined accordingly to propagate the label of each sample. High-confidence samples are then collected for self-training the model and updating the templates concurrently to handle large scale. Experiments on various benchmark data sets and comparisons to several state-of-the-art methods demonstrate the effectiveness and efficiency of our algorithm. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/TCSVT.2014.2355692 | Circuits and Systems for Video Technology, IEEE Transactions |
Keywords | Field | DocType |
low rank,metric learning,object tracking,online learning,semisupervised learning,computational complexity,testing,computational modeling,stochastic processes,learning artificial intelligence | Computer vision,BitTorrent tracker,Data set,Semi-supervised learning,Pattern recognition,Computer science,Stochastic process,Video tracking,Artificial intelligence,Overfitting,Computational complexity theory,Bilinear interpolation | Journal |
Volume | Issue | ISSN |
25 | 6 | 1051-8215 |
Citations | PageRank | References |
10 | 0.53 | 37 |
Authors | ||
5 | ||