Low Resolution Information Also Matters: Learning Multi-Resolution Representations for Person Re-Identification

05/26/2021
by   Guoqing Zhang, et al.
3

As a prevailing task in video surveillance and forensics field, person re-identification (re-ID) aims to match person images captured from non-overlapped cameras. In unconstrained scenarios, person images often suffer from the resolution mismatch problem, i.e., Cross-Resolution Person Re-ID. To overcome this problem, most existing methods restore low resolution (LR) images to high resolution (HR) by super-resolution (SR). However, they only focus on the HR feature extraction and ignore the valid information from original LR images. In this work, we explore the influence of resolutions on feature extraction and develop a novel method for cross-resolution person re-ID called Multi-Resolution Representations Joint Learning (MRJL). Our method consists of a Resolution Reconstruction Network (RRN) and a Dual Feature Fusion Network (DFFN). The RRN uses an input image to construct a HR version and a LR version with an encoder and two decoders, while the DFFN adopts a dual-branch structure to generate person representations from multi-resolution images. Comprehensive experiments on five benchmarks verify the superiority of the proposed MRJL over the relevent state-of-the-art methods.

READ FULL TEXT

page 1

page 3

page 5

page 6

research
09/16/2021

Resolution based Feature Distillation for Cross Resolution Person Re-Identification

Person re-identification (re-id) aims to retrieve images of same identit...
research
08/16/2019

Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification

Person re-identification (re-ID) aims at matching images of the same ide...
research
06/24/2019

Resolution-invariant Person Re-Identification

Exploiting resolution invariant representation is critical for person Re...
research
07/25/2019

Learning Resolution-Invariant Deep Representations for Person Re-Identification

Person re-identification (re-ID) solves the task of matching images acro...
research
01/12/2021

Resolution-invariant Person ReID Based on Feature Transformation and Self-weighted Attention

Person Re-identification (ReID) is a critical computer vision task which...
research
10/08/2019

Person re-identification based on Res2Net network

Person re-identification (re-ID) has been gaining in popularity in the r...
research
03/09/2020

Domain Adversarial Training for Infrared-colour Person Re-Identification

Person re-identification (re-ID) is a very active area of research in co...

Please sign up or login with your details

Forgot password? Click here to reset