ECCV2022 行人重识别论文汇总

跨模态reid

971 Optimal Transport for Label-Efficient Visible-Infrared Person Re-Identification
3677 Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification
4836 Cross-Modality Transformer for Visible-Infrared Person Re-Identification

自监督reid

1161 PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification

域可泛化性reid (DG reid)

1198 Adaptive Cross-Domain Learning for Generalizable Person Re-Identification
2766 Dynamically Transformed Instance Normalization Network for Generalizable Person Re-Identification
3409 Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification

私货
分类DG/UDA论文

249 Unknown-Oriented Learning for Open Set Domain Adaptation
1762 MoDA: Map style transfer for self-supervised Domain Adaptation of embodied agents
1986 Feature Representation Learning for Unsupervised Cross-domain Image Retrieva
2583 On Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization and Beyond
2862 A Broad Study of Pre-training for Domain Generalization and Adaptation
3660 Domain Generalization by Mutual-Information Regularization with Pre-trained Models
4593 Cross-Domain Ensemble Distillation for Domain Generalization
7710 Attention Diversification for Domain Generalization
7845 MVDG: A Unified Multi-view Framework for Domain Generalization MVDG

  • 2
    点赞
  • 16
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
基于图神经网络的行人重识别是一种用于解决行人重识别问题的方法。在Yantao Shen的论文《Person Re-identification with Deep Similarity-Guided Graph Neural Network》中提出了一种名为Similarity-Guided Graph Neural Network (SGGNN)的模型。该模型的主要贡献是通过图神经网络来建模行人之间的相似性,并利用这些相似性来改善行人重识别的效果。 行人重识别是指在视频监控场景中,通过比对不同摄像头中的行人图像,将同一个行人在不同摄像头中的出现进行匹配和识别的任务。然而,由于摄像头视角、光照条件和行人姿态等因素的影响,行人重识别面临着许多挑战。其中之一就是在其他行人干扰的情况下进行准确的识别。 SGGNN模型通过构建一个图,将行人之间的相似性建模为图的边。然后,利用图神经网络来学习行人特征之间的关系,并生成每对行人之间的相似性分数。在进行行人重识别时,可以根据这些相似性分数来进行匹配和识别,从而提高准确性和鲁棒性。 总结来说,基于图神经网络的行人重识别是一种利用图模型来建模行人之间的相似性,并通过学习这些相似性来改善行人重识别效果的方法。SGGNN是其中的一个具体模型,在处理其他行人干扰的情况下尤为有效。<span class="em">1</span><span class="em">2</span><span class="em">3</span> #### 引用[.reference_title] - *1* *2* [行人重识别 PCB-RPP,SGGNN](https://blog.csdn.net/SIGAI_CSDN/article/details/82911843)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v93^chatsearchT3_1"}}] [.reference_item style="max-width: 50%"] - *3* [ECCV 2020 | 腾讯优图8篇论文入选,涵盖目标跟踪、行人重识别、人脸识别等领域...](https://blog.csdn.net/moxibingdao/article/details/107502885)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v93^chatsearchT3_1"}}] [.reference_item style="max-width: 50%"] [ .reference_list ]
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值