Person Re-Identification by Localizing Discriminative Regions

Tanzila Rahman, Mrigank Rochan and Yang Wang

Abstract

Person re-identification is a challenging task of matching a person’s image across multiple images captured from different camera views. Recently, deep learning based approaches have been proposed that show promising performance on this task. However, most of these approaches use whole image features to compute the similarity between images. This is not very intuitive since not all the regions in an image contain information about the person identity. In this paper, we introduce an end-to-end Siamese convolutional neural network that firstly localizes discriminative salient image regions and then computes the similarity based on these image regions in conjunction with the whole image. We use Spatial Transformer Networks (STN) for localizing salient regions.

Session

Posters

Files

PDF iconPaper (PDF)

DOI

10.5244/C.31.55
https://dx.doi.org/10.5244/C.31.55

Citation

Tanzila Rahman, Mrigank Rochan and Yang Wang. Person Re-Identification by Localizing Discriminative Regions. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 55.1-55.12. BMVA Press, September 2017.

Bibtex

            @inproceedings{BMVC2017_55,
                title={Person Re-Identification by Localizing Discriminative Regions},
                author={Tanzila Rahman, Mrigank Rochan and Yang Wang},
                year={2017},
                month={September},
                pages={55.1-55.12},
                articleno={55},
                numpages={12},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.55},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.55}
            }