dc.contributor.author | Li, M | en_US |
dc.contributor.author | Zhu, X | en_US |
dc.contributor.author | Gong, S | en_US |
dc.contributor.author | European Conference on Computer Vision | en_US |
dc.date.accessioned | 2019-01-03T16:36:20Z | |
dc.date.available | 2018-07-03 | en_US |
dc.date.issued | 2018-09-08 | en_US |
dc.identifier.isbn | 9783030012243 | en_US |
dc.identifier.issn | 0302-9743 | en_US |
dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/54066 | |
dc.description.abstract | © 2018, Springer Nature Switzerland AG. Most existing person re-identification (re-id) methods rely on supervised model learning on per-camera-pair manually labelled pairwise training data. This leads to poor scalability in practical re-id deployment due to the lack of exhaustive identity labelling of image positive and negative pairs for every camera pair. In this work, we address this problem by proposing an unsupervised re-id deep learning approach capable of incrementally discovering and exploiting the underlying re-id discriminative information from automatically generated person tracklet data from videos in an end-to-end model optimisation. We formulate a Tracklet Association Unsupervised Deep Learning (TAUDL) framework characterised by jointly learning per-camera (within-camera) tracklet association (labelling) and cross-camera tracklet correlation by maximising the discovery of most likely tracklet relationships across camera views. Extensive experiments demonstrate the superiority of the proposed TAUDL model over the state-of-the-art unsupervised and domain adaptation re-id methods using six person re-id benchmarking datasets. | en_US |
dc.format.extent | 772 - 788 | en_US |
dc.rights | This is a pre-copyedited, author-produced version of an article accepted for publication in European Conference on Computer Vision following peer review. The version of record is available https://link.springer.com/chapter/10.1007%2F978-3-030-01225-0_45 | |
dc.title | Unsupervised Person Re-identification by Deep Learning Tracklet Association | en_US |
dc.type | Conference Proceeding | |
dc.rights.holder | © Springer Nature Switzerland AG 2018 | |
dc.identifier.doi | 10.1007/978-3-030-01225-0_45 | en_US |
pubs.notes | No embargo | en_US |
pubs.publication-status | Published | en_US |
pubs.volume | 11208 LNCS | en_US |
dcterms.dateAccepted | 2018-07-03 | en_US |
rioxxterms.funder | Default funder | en_US |
rioxxterms.identifier.project | Default project | en_US |
qmul.funder | Newton Advanced Fellowship: Person Re-Identification::Royal Society | en_US |
qmul.funder | Newton Advanced Fellowship: Person Re-Identification::Royal Society | en_US |