Multiple-Shot Person Re-identification by HPE Signature

Loris Bazzani, Marco Cristani, Alessandro Perina, Michela Farenzena, Vittorio MurinoICPR 2010 · OpenReview

Abstract

In this paper, we propose a novel appearance-based method for person re-identification, that condenses a set of frames of the same individual into a highly informative signature, called Histogram Plus Epitome, HPE. It incorporates complementary global and local statistical descriptions of the human appearance, focusing on the overall chromatic content, via histograms representation, and on the presence of recurrent local patches, via epitome estimation. The matching of HPEs provides optimal performances against low resolution, occlusions, pose and illumination variations, defining novel state-of-the-art results on all the datasets considered.
BibTeX
@inproceedings{bazzani2010multiple,
  author = {Loris Bazzani and Marco Cristani and Alessandro Perina and Michela Farenzena and Vittorio Murino},
  title = {{Multiple-Shot Person Re-identification by HPE Signature}},
  booktitle = {ICPR},
  year = {2010},
  url = {https://openreview.net/forum?id=T82duuyM8P},
}

Loading related content...

Figure