Object Tracking using Reformative Transductive Learning with Sample Variational Correspondence

Tao Zhuo, Peng Zhang, Yanning Zhang, Wei Huang, Hichem Sahli

Research output: Chapter in Book/Report/Conference proceedingConference paper

3 Citations (Scopus)


Tracking-by-learning strategies have effectively resolved many challenging problems for visual tracking. When labeled samples are limited, the learning performance can be improved by exploiting unlabeled ones. Thus, a key issue for semisupervised learning is the label assignment of the unlabeled samples, which is the principal focus of transductive learning.
Unfortunately, the optimization schemes employed by the transductive learning is hard to be applied to online tracking because of its large amount of computation for sample labeling. In this paper, a reformative transductive learning was proposed with the variational correspondence between the learning samples, which are utilized to build an effective matching cost function for more efficient label assignment during the learning of representative separators.By using a weighted accumulative average to update coefficients via a fixed budget of support vectors, the proposed tracking has been demonstrated to outperform most of the state-of-art trackers by comprehensive experiments on various benchmark videos.
Original languageEnglish
Title of host publicationACM Inter. Conf. in Multimedia
Publication statusPublished - 2014
Event22nd ACM International Conference on Multimedia - Orlando, FL, United States
Duration: 3 Nov 20147 Nov 2014


Conference22nd ACM International Conference on Multimedia
CountryUnited States
CityOrlando, FL


  • tracking
  • Scene analysis,


Dive into the research topics of 'Object Tracking using Reformative Transductive Learning with Sample Variational Correspondence'. Together they form a unique fingerprint.

Cite this