[Conference Paper] Saliency Weighted Features for Person Re-Identification
Title: Saliency Weighted Features for Person Re-Identification
Authors : Niki Martinel , Christian Micheloni , Gian Luca Foresti
Conference: European Conference on Computer Vision (ECCV)Proposed system architecture based on ve main stages: kernelized saliency
computation, feature extraction, dimensionality reduction, multiple metric learning
and distance fusion.The solution, inspired by human gazing capabilities, wants to identify the salient regions of a given person. Such regions are used as a weighting tool in the image feature extraction process.
Then, such novel representation is combined with a set of other visual features in a pairwise-based multiple metric learning framework.
Finally, the learned metrics are fused to get the distance between image pairs and to re-identify a person.
The novelty of the approach is also supported by the provided results.
Our approach overall outperforms the best state-of-the-art solutions on the three most
challenging benchmark datasets.
