BiCov: a novel image representation for person re-identification and face verification
Citations Over TimeTop 1% of 2012 papers
Abstract
This paper proposes a novel image representation which can properly handle both background and illumination variations. It is therefore adapted to the person/face reidentification tasks, avoiding the use of any additional pre-processing steps such as foreground-background separation or face and body part segmentation. This novel representation relies on the combination of Biologically Inspired Features (BIF) and covariance descriptors used to compute the similarity of the BIF features at neighboring scales. Hence, we will refer to it as the BiCov representation. To show the effectiveness of BiCov, this paper conducts experiments on two person re-identification tasks (VIPeR and ETHZ) and one face verification task (LFW), on which it improves the current state-of-the-art performance.
Related Papers
- → The Identification Zoo: Meanings of Identification in Econometrics(2019)151 cited
- → Elections and Representation in Local Government: A Victorian Case Study(2004)22 cited
- The Identification Zoo - Meanings of Identification in Econometrics(2018)
- Problems and Solutions of the Socialization of Identification Agencies(2009)
- [Identification based on medical findings].(1988)