MEMF: Multi-level-attention embedding and multi-layer-feature fusion model for person re-identification

Sun, Jia; Li, Yanfeng; Chen, Houjin; Zhang, Bin; Zhu, Jinlei

doi:10.1016/j.patcog.2021.107937

Cited by 25 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A multi-level attention and fusion model was proposed in [118]. Multi-level attention module has helped in learning the global level features while the multi-layer fusion module has helped in increasing the feature expression at fine granular level.…”

Section: Attention-based Approachesmentioning

confidence: 99%

“…The cluttered background, if not efficiently removed or suppressed, inversely effects the performance of re-id solution. Since the attention based mechanism inherently focus and highlight the attentive parts/ regions on a person image, the top three re-id solutions which perform the best even in case of cluttered background also employed attention based mechanisms to exclude the background information [115] and learns multi-level attention in different ways [118] and fuse the information learnt from various levels and branches [119]. Generally, these approaches capture the foreground attention features using either the encoder decoder architecture or the multi-level attention modules.…”

Section: Deep Learning Conjecturementioning

confidence: 99%

See 1 more Smart Citation

Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends

Zahra¹,

Perwaiz²,

Shahzad³

et al. 2022

Preprint

View full text Add to dashboard Cite

Person re-identification (Re-ID) is one of the primary components of an automated visual surveillance system. It aims to automatically identify/search persons in a multi-camera network having non-overlapping field-of-views. Owing to its potential in various applications and research significance, a plethora of deep learning based re-Id approaches have been proposed in the recent years. However, there exist several vision related challenges, e.g., occlusion, pose scale & viewpoint variance, background clutter, person misalignment and cross-domain generalization across camera modalities, which makes the problem of re-Id still far from being solved. Majority of the proposed approaches directly or indirectly aim to solve one or multiple of these existing challenges. In this context, a comprehensive review of current re-ID approaches in solving theses challenges is needed to analyze and focus on particular aspects for further advancements. At present, such a focused review does not exist and henceforth in this paper, we have presented a systematic challenge-specific literature survey of 230+ papers between the years of 2015-21. For the first time a survey of this type have been presented where the person re-Id approaches are reviewed in such solution-oriented perspective. Moreover, we have presented several diversified prominent developing trends in the respective research domain which will provide a visionary perspective regarding ongoing person re-Id research and eventually help to develop practical real world solutions. Scope/Objective of the ReviewIn this paper, we have targeted the most popular challenges in person re-id to perform systematic challenge-wise review of the published approaches. In this context, we have collected papers from top conferences and journals for the years from 2015 to 2021. The progress in papers addressing each challenge and its influence on published results is

show abstract

Section: Attention-based Approachesmentioning

confidence: 99%

Section: Deep Learning Conjecturementioning

confidence: 99%

Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends

Zahra¹,

Perwaiz²,

Shahzad³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…This inspires us to design the global model as a generic term to solve the overfitting problem and the personalized model as a penalty term to meet the personalized needs of heterogeneous data, respectively. Meanwhile, an idea of fusion based on the neural network layers was suggested in [26]. And then, a layer-based federated learning method was developed in [27], which requires a portion of the raw data for the server to train the fused weights.…”

Section: Introductionmentioning

confidence: 99%

Cross-Fusion Rule for Personalized Federated Learning

Yang

Chen

Shen

et al. 2023

Preprint

View full text Add to dashboard Cite

“…Person re-identification (ReID) is the task of matching a specific person among multiple non-overlapping cameras, which has wide applications in the field of video surveillance 1 . Most of the progress mainly focus on homogeneous images 2 . However, visible cameras are limited in surveillance when lighting is either poor or unavailable, e.g., at night 3 Intuitively, visible and infrared images are intrinsically distinct and heterogeneous.…”

Section: Introductionmentioning

confidence: 99%

A sample diversity and identity consistency based cross-modality model for visible-infrared person re-identification

Sun

Li²,

Chen³

et al. 2022

Fourteenth International Conference on Digital Image Processing (ICDIP 2022)

View full text Add to dashboard Cite

Visible-infrared person re-identification (VI-ReID) aims to search person images across cameras of different modalities, which can address the limitation of visible-based ReID in dark environments. It is a very challenging task, as images of the same identity have huge discrepancy in different modalities. To address this problem, a cross-modality ReID model based on sample diversity and identity consistency is proposed in this paper. For sample diversity, auxiliary images are introduced based on the idea of information transfer. The auxiliary images combine the information of visible images and infrared images, and can improve the diversity of input data and robustness of the network. For identity consistency, homogeneous distance loss and heterogeneous distance loss are developed from four different perspectives to shorten the distance between the samples of same identities. Extensive experimental results demonstrate the effectiveness of the proposed method.

show abstract

MEMF: Multi-level-attention embedding and multi-layer-feature fusion model for person re-identification

Cited by 25 publications

References 17 publications

Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends

Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends

Cross-Fusion Rule for Personalized Federated Learning

A sample diversity and identity consistency based cross-modality model for visible-infrared person re-identification

Contact Info

Product

Resources

About