CoDeL: A Human Co-detection and Labeling Framework
Refereed conference paper presented and published in conference proceedings


Times Cited
Web of Science4WOS source URL (as at 13/10/2020) Click here for the latest count
Altmetrics Information
.

Other information
AbstractWe propose a co-detection and labeling (CoDeL) framework to identify persons that contain self-consistent appearance in multiple images. Our CoDeL model builds upon the deformable part-based model to detect human hypotheses and exploits cross-image correspondence via a matching classifier. Relying on a Gaussian process, this matching classifier models the similarity of two hypotheses and efficiently captures the relative importance contributed by various visual features, reducing the adverse effect of scattered occlusion. Further, the detector and matching classifier together make our model fit into a semi-supervised co-training framework, which can get enhanced results with a small amount of labeled training data. Our CoDeL model achieves decent performance on existing and new benchmark datasets.
All Author(s) ListShi JP, Liao RJ, Jia JY
Name of ConferenceIEEE International Conference on Computer Vision (ICCV)
Start Date of Conference01/12/2013
End Date of Conference08/12/2013
Place of ConferenceSydney
Country/Region of ConferenceAustralia
Detailed descriptionorganized by IEEE,
Year2013
Month1
Day1
PublisherIEEE
Pages2096 - 2103
eISBN978-1-4799-2839-2
ISSN1550-5499
LanguagesEnglish-United Kingdom
Web of Science Subject CategoriesComputer Science; Computer Science, Artificial Intelligence

Last updated on 2020-14-10 at 03:03