2020
DOI: 10.1016/j.neucom.2019.12.100
|View full text |Cite
|
Sign up to set email alerts
|

Hetero-Center loss for cross-modality person Re-identification

Abstract: Cross-modality person re-identification is a challenging problem which retrieves a given pedestrian image in RGB modality among all the gallery images in infrared modality. The task can address the limitation of RGB-based person Re-ID in dark environments. Existing researches mainly focus on enlarging inter-class differences of feature to solve the problem. However, few studies investigate improving intra-class cross-modality similarity, which is important for this issue. In this paper, we propose a novel loss… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
84
0

Year Published

2020
2020
2022
2022

Publication Types

Select...
5
3
1

Relationship

1
8

Authors

Journals

citations
Cited by 167 publications
(109 citation statements)
references
References 37 publications
0
84
0
Order By: Relevance
“…As a result, a cross-modality model can learn to capture information shared by different modalities during the training process. More details of the hetero-centre loss can be refferred to [48]. Dispite using the IMSLoss for refined multimodality feature learning, the cross-entropy loss L ce (Eq.…”
Section: Inter-modality Similarity Lossmentioning
confidence: 99%
“…As a result, a cross-modality model can learn to capture information shared by different modalities during the training process. More details of the hetero-centre loss can be refferred to [48]. Dispite using the IMSLoss for refined multimodality feature learning, the cross-entropy loss L ce (Eq.…”
Section: Inter-modality Similarity Lossmentioning
confidence: 99%
“…By considering that our proposed method in this paper is closely related to loss function, we only give a rough introduction of person reidentification methods based on loss function. It is worth noting that many other inspiring methods have been proposed to address the person reidentification tasks, e.g., pose-guided methods [26], crossmodality based methods [27], and unsupervised learning based methods [28]. One can learn about more detailed information in [29].…”
Section: Related Workmentioning
confidence: 99%
“…Recently, some scholars have investigated a better loss function. For example, Zhu et al [8] created a heterogenous Hetero-Center (HC) loss to narrow the gaps between images of the two modalities.…”
Section: Introductionmentioning
confidence: 99%