2020
DOI: 10.1609/aaai.v34i07.6857
|View full text |Cite
|
Sign up to set email alerts
|

Relation Network for Person Re-Identification

Abstract: Person re-identification (reID) aims at retrieving an image of the person of interest from a set of images typically captured by multiple cameras. Recent reID methods have shown that exploiting local features describing body parts, together with a global feature of a person image itself, gives robust feature representations, even in the case of missing body parts. However, using the individual part-level features directly, without considering relations between body parts, confuses differentiating identities of… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
42
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
4
1

Relationship

0
9

Authors

Journals

citations
Cited by 104 publications
(42 citation statements)
references
References 32 publications
0
42
0
Order By: Relevance
“…In the first part of proposed scheme, that is, feature extraction , CNN is employed to extract an initial feature map f$f$ with a size of h×w×c$h \times w \times c$ (h,w,c$h, w, c$ are height, width, and the number of channels, respectively) from a person image. In the second part, that is, local/global‐aware feature generation , feature map f$f$ is divided equally into k$k$ horizontal stripes, which follows the operations in references [20, 29, 48]. Each stripe has a smaller receptive field than the global‐level feature f$f$.…”
Section: Methodsmentioning
confidence: 99%
“…In the first part of proposed scheme, that is, feature extraction , CNN is employed to extract an initial feature map f$f$ with a size of h×w×c$h \times w \times c$ (h,w,c$h, w, c$ are height, width, and the number of channels, respectively) from a person image. In the second part, that is, local/global‐aware feature generation , feature map f$f$ is divided equally into k$k$ horizontal stripes, which follows the operations in references [20, 29, 48]. Each stripe has a smaller receptive field than the global‐level feature f$f$.…”
Section: Methodsmentioning
confidence: 99%
“…Also, Huang et al [25] propose 3-Dimension Transmissible Attention (3DTA) that cooperatively utilizes channel attention and spatial attention, with a group loss to optimize the feature distances. In [31], relation network puts forward a global attention mechanism with relation-aware and has achieved superior performance. Zhang et al [32] focus on different attributes of a person including sex, hair, etc.…”
Section: Related Work a Supervised Person Re-identificationmentioning
confidence: 99%
“…For example, semantic feature learning is studied via multistage ROI pooling in the work [1]. In the work [2], relations among individual body parts are explored through a GCP network. Additionally, metric learning aims to map semantically similar persons from some manifold onto metrically close person points in another space.…”
Section: Introductionmentioning
confidence: 99%
“…(1) We propose a deep camera-aware metric learning (DCAML) model to discover the relationship between camera and identity, where camera-level and identity-level information jointly contribute to the retrieval accuracy (2) We develop a dynamic training strategy to integrate multiple metrics as a unified optimization objective…”
Section: Introductionmentioning
confidence: 99%