Semi-supervised regression with temporal image sequences

10 years 2 months ago
Semi-supervised regression with temporal image sequences
We consider a semi-supervised regression setting where we have temporal sequences of partially labeled data, under the assumption that the labels should vary slowly along a sequence, but that nearby points in input space may have drastically different labels. The setting is motivated by problems such as determining the time of the day or the level of air visibility given an image of a landscape, which is hard because the time or visibility label is related in a complex way with the pixel values. We propose a regression framework regularized with a graph Laplacian prior, where the graph is given by the sequential information. We show this outperforms graphs learned in an unsupervised way for detecting the rotation of MNIST digits and estimating the time of day an image is captured, and provides modest improvement in the challenging visibility problem.
Ling Xie, Miguel Á. Carreira-Perpiñ&
Added 12 Feb 2011
Updated 12 Feb 2011
Type Journal
Year 2010
Where ICIP
Authors Ling Xie, Miguel Á. Carreira-Perpiñán, Shawn Newsam
Comments (0)