Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/115992
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Sequential person recognition in photo albums with a recurrent network |
Author: | Li, Y. Lin, G. Zhuang, B. Liu, L. Shen, C. van den Hengel, A. |
Citation: | Proceedings / 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 |
Publisher: | IEEE |
Publisher Place: | online |
Issue Date: | 2017 |
Series/Report no.: | IEEE Conference on Computer Vision and Pattern Recognition |
ISBN: | 9781538604571 |
ISSN: | 1063-6919 |
Conference Name: | 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017) (21 Jul 2017 - 26 Jul 2017 : Honolulu, Hawaii) |
Statement of Responsibility: | Yao Li, Guosheng Lin, Bohan Zhuang, Lingqiao Liu, Chunhua Shen, Anton van den Hengel |
Abstract: | Recognizing 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. |
Rights: | © 2017 IEEE |
DOI: | 10.1109/CVPR.2017.600 |
Published version: | http://dx.doi.org/10.1109/cvpr.2017.600 |
Appears in Collections: | Aurora harvest 8 Australian Institute for Machine Learning publications Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.