Learning Mid-level Filters for Person Re-identification
Top Cited Papers
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 144-151
- https://doi.org/10.1109/cvpr.2014.26
Abstract
In this paper, we propose a novel approach of learning mid-level filters from automatically discovered patch clusters for person re-identification. It is well motivated by our study on what are good filters for person re-identification. Our mid-level filters are discriminatively learned for identifying specific visual patterns and distinguishing persons, and have good cross-view invariance. First, local patches are qualitatively measured and classified with their discriminative power. Discriminative and representative patches are collected for filter learning. Second, patch clusters with coherent appearance are obtained by pruning hierarchical clustering trees, and a simple but effective cross-view training strategy is proposed to learn filters that are view-invariant and discriminative. Third, filter responses are integrated with patch matching scores in RankSVM training. The effectiveness of our approach is validated on the VIPeR dataset and the CUHK01 dataset. The learned mid-level features are complementary to existing handcrafted low-level features, and improve the best Rank-1 matching rate on the VIPeR dataset by 14%.Keywords
This publication has 20 references indexed in Scilit:
- DeepReID: Deep Filter Pairing Neural Network for Person Re-identificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- POP: Person Re-identification Post-rank OptimisationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Local Fisher Discriminant Analysis for Pedestrian Re-identificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Learning Locally-Adaptive Decision Functions for Person VerificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Intelligent multi-camera video surveillance: A reviewPattern Recognition Letters, 2013
- PCCA: A new approach for distance learning from sparse pairwise constraintsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- BiCov: a novel image representation for person re-identification and face verificationPublished by British Machine Vision Association and Society for Pattern Recognition ,2012
- Person Re-identification by AttributesPublished by British Machine Vision Association and Society for Pattern Recognition ,2012
- Person Re-Identification by Support Vector RankingPublished by British Machine Vision Association and Society for Pattern Recognition ,2010
- Shape and Appearance Context ModelingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007