Leveraging local neighborhood topology for large scale person re-identification

Svebor Karaman, Giuseppe Lisanti, Andrew D. Bagdanov, Alberto Del Bimbo

    Research output: Contribution to journalArticleResearchpeer-review

    19 Citations (Scopus)


    © 2014 Elsevier Ltd. In this paper we describe a semi-supervised approach to person re-identification that combines discriminative models of person identity with a Conditional Random Field (CRF) to exploit the local manifold approximation induced by the nearest neighbor graph in feature space. The linear discriminative models learned on few gallery images provides coarse separation of probe images into identities, while a graph topology defined by distances between all person images in feature space leverages local support for label propagation in the CRF. We evaluate our approach using multiple scenarios on several publicly available datasets, where the number of identities varies from 28 to 191 and the number of images ranges between 1003 and 36 171. We demonstrate that the discriminative model and the CRF are complementary and that the combination of both leads to significant improvement over state-of-the-art approaches. We further demonstrate how the performance of our approach improves with increasing test data and also with increasing amounts of additional unlabeled data.
    Original languageEnglish
    Pages (from-to)3767-3778
    JournalPattern Recognition
    Issue number12
    Publication statusPublished - 1 Dec 2014


    • 3DPeS
    • CAVIAR
    • CMV100
    • Conditional random field
    • ETHZ
    • Re-identification
    • Semi-supervised


    Dive into the research topics of 'Leveraging local neighborhood topology for large scale person re-identification'. Together they form a unique fingerprint.

    Cite this