Sequential person recognition in photo albums with a recurrent network

Simple item page
dc.contributor.authorLi, Y.
dc.contributor.authorLin, G.
dc.contributor.authorZhuang, B.
dc.contributor.authorLiu, L.
dc.contributor.authorShen, C.
dc.contributor.authorvan den Hengel, A.
dc.contributor.conference30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017) (21 Jul 2017 - 26 Jul 2017 : Honolulu, Hawaii)
dc.date.issued2017
dc.description.abstractRecognizing the identities of people in everyday photos is still a very challenging problem for machine vision, due to issues such as non-frontal faces, changes in clothing, location, lighting. Recent studies have shown that rich relational information between people in the same photo can help in recognizing their identities. In this work, we propose to model the relational information between people as a sequence prediction task. At the core of our work is a novel recurrent network architecture, in which relational information between instances labels and appearance are modeled jointly. In addition to relational cues, scene context is incorporated in our sequence prediction model with no additional cost. In this sense, our approach is a unified framework for modeling both contextual cues and visual appearance of person instances. Our model is trained end-to-end with a sequence of annotated instances in a photo as inputs, and a sequence of corresponding labels as targets. We demonstrate that this simple but elegant formulation achieves state-of-the-art performance on the newly released People In Photo Albums (PIPA) dataset.
dc.description.statementofresponsibilityYao Li, Guosheng Lin, Bohan Zhuang, Lingqiao Liu, Chunhua Shen, Anton van den Hengel
dc.identifier.citationProceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2017, vol.2017-January, pp.5660-5668
dc.identifier.doi10.1109/CVPR.2017.600
dc.identifier.isbn9781538604571
dc.identifier.issn1063-6919
dc.identifier.orcidvan den Hengel, A. [0000-0003-3027-8364]
dc.identifier.urihttp://hdl.handle.net/2440/115992
dc.language.isoen
dc.publisherIEEE
dc.publisher.placeonline
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognition
dc.rights© 2017 IEEE
dc.source.urihttps://doi.org/10.1109/cvpr.2017.600
dc.titleSequential person recognition in photo albums with a recurrent network
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Computer Science publications
Australian Institute for Machine Learning publications