SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-Identification

by   Xing Fan, et al.
Megvii Technology Limited
Zhejiang University

Holistic person re-identification (ReID) has received extensive study in the past few years and achieves impressive progress. However, persons are often occluded by obstacles or other persons in practical scenarios, which makes partial person re-identification non-trivial. In this paper, we propose a spatial-channel parallelism network (SCPNet) in which each channel in the ReID feature pays attention to a given spatial part of the body. The spatial-channel corresponding relationship supervises the network to learn discriminative feature for both holistic and partial person re-identification. The single model trained on four holistic ReID datasets achieves competitive accuracy on these four datasets, as well as outperforms the state-of-the-art methods on two partial ReID datasets without training.


page 2

page 10


STNReID : Deep Convolutional Networks with Pairwise Spatial Transformer Networks for Partial Person Re-identification

Partial person re-identification (ReID) is a challenging task because on...

Short Range Correlation Transformer for Occluded Person Re-Identification

Occluded person re-identification is one of the challenging areas of com...

Hierarchical and Efficient Learning for Person Re-Identification

Recent works in the person re-identification task mainly focus on the mo...

WiPIN: Operation-free Person Identification using WiFi Signals

Person identification is critical for sensitive applications such as sys...

Dynamic Prototype Mask for Occluded Person Re-Identification

Although person re-identification has achieved an impressive improvement...

Omni-directional Feature Learning for Person Re-identification

Person re-identification (PReID) has received increasing attention due t...

Please sign up or login with your details

Forgot password? Click here to reset