Multiple kernel tracking with SSD

By Gregory Hager, Maneesh Dewan, Charles V. Stewart. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004., 2004

298 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/270d3d614f519f4bcc1b4a28f0d3c5bead86a46b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Robust Fragments-based Tracking using the Integral Histogram (2006, background): “We present extensive experimental results on challenging sequences, which demonstrate the robust tracking achieved by our algorithm (even with the use of only gray-scale (noncolor) information).”
Spatiograms versus histograms for region-based tracking (2005, methodology): “Recently, Hager et al. [4] developed a connection be-tween these two seemingly unrelated techniques by proposing to use multiple spatially-weighted histograms.”
Objective comparison of particle tracking methods (2014, methodology): “METHOD 4: PARAMETERS The user parameters of this method (and typical values) are:  Number of iterations of convolution with the Gaussian kernel (10-500).”
Distribution fields for tracking (2012, methodology): “In addition, our tracker is most similar in spirit to the Multiple Kernel Tracker [13] (MKT), and so we implemented and ran it on the same suite.”
Efficient mean-shift tracking via a new similarity measure (2005, background): “Among the various tracking algorithms, mean shift tracking algorithms have recently become popular due to their simplicity and robustness [5, 10, 8, 20].”
Face tracking and recognition with visual constraints in real-world videos (2008, background): “Numerous approaches to target modeling have attempted to tackle these issues using view-based appearance models [4], contour models [9], 3D models [11], mixture models [10], and kernel representations [6, 8], among others.”