Multi-scale representation with graph learning for video-based person re-identification

Sheng Chen; Hongbo Zhao; Zhijun He; Wenquan Feng

doi:10.1117/12.2604707

5 October 2021 Multi-scale representation with graph learning for video-based person re-identification

Sheng Chen, Hongbo Zhao, Zhijun He, Wenquan Feng

Proceedings Volume 11911, 2nd International Conference on Computer Vision, Image, and Deep Learning; 1191113 (2021) https://doi.org/10.1117/12.2604707
Event: 2nd International Conference on Computer Vision, Image and Deep Learning, 2021, Liuzhou, China

Abstract

Video-based person re-identification (Re-ID) has drawn more attention as video surveillance could offer richer spatial and temporal information to potentially reduce visual ambiguities and occlusion. For visual ambiguities, multi-scale features are beneficial for distinguishing similar pedestrian sequences by different semantic information. For occlusion, Graph Convolutional Network (GCN) could effectively leverage the complementary information with node pairs for Re- ID task. In this paper, we propose a novel Multi-Scale Representation with Graph Learning (MSR-GL) network consisting of three branches: global branch, shallow branch and graph branch. The global branch and shallow branch extract multi-scale features from different layers of CNN backbone. Specially, an extra Bottleneck module is introduced for shallow feature maps, in which the parameters are independent with other branches. For graph branch, the adjacency relationships are dynamically modeled through a temporal-spatial symmetrical transformation between nodes. Then, the node features are updated by adjacency matrix and aggregated to video-level graph features. We conduct extensive experiments on three widely-adopted benchmarks (i.e. MARS, DukeMTMC-VideoReID and iLIDS-VID). Results show that we achieve the superior results compared with several recent state-of-the-art methods with 90.28% rank1 and 85.20% mAP on MARS.

Citation Download Citation

Sheng Chen, Hongbo Zhao, Zhijun He, and Wenquan Feng "Multi-scale representation with graph learning for video-based person re-identification", Proc. SPIE 11911, 2nd International Conference on Computer Vision, Image, and Deep Learning, 1191113 (5 October 2021); https://doi.org/10.1117/12.2604707

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Mars

Visualization

Multiscale representation

Video

Video surveillance

Neural networks

3D modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years