Cross-modal Local Shortest Path and Global Enhancement for Visible-Thermal Person Re-Identification
Not on the map. Why?
Abstract (arXiv)
In addition to considering the recognition difficulty caused by human posture and occlusion, it is also necessary to solve the modal differences caused by different imaging systems in the Visible-Thermal cross-modal person re-identification (VT-ReID) task. In this paper,we propose the Cross-modal Local Shortest Path and Global Enhancement (CM-LSP-GE) modules,a two-stream network based on joint learning of local and global features. The core idea of our paper is to use local feature alignment to solve occlusion problem, and to solve modal difference by strengthening global feature. Firstly, Attention-based two-stream ResNet network is designed to extract dual-modality features and map to a unified feature space. Then, to solve the cross-modal person pose and occlusion problems, the image are cut horizontally into several equal parts to obtain local features and the shortest path in local features between two graphs is used to achieve the fine-grained local feature alignment. Thirdly, a batch normalization enhancement module applies global features to enhance strategy, resulting in difference enhancement between different classes. The multi granularity loss fusion strategy further improves the performance of the algorithm. Finally, joint learning mechanism of local and global features is used to improve cross-modal person re-identification accuracy. The experimental results on two typical datasets show that our model is obviously superior to the most state-of-the-art methods. Especially, on SYSU-MM01 datasets, our model can achieve a gain of 2.89%and 7.96% in all search term of Rank-1 and mAP. The source code will be released soon.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 45 references that are in the map. First posted on arXiv 9 Jun 2022.
Builds on
22 of 45 references.
References · 22
- 2017Squeeze-and-Excitation Networkscited by 4,763
- 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
- 2018CBAM: Convolutional Block Attention Modulecited by 2,463
- 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 547
- 2020ResNeSt: Split-Attention Networkscited by 445
- 2019Selective Kernel Networkscited by 401
- 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
- 2019RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignmentcited by 102
- 2017A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Rankingcited by 74
- 2020Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identificationcited by 71
- 2017AlignedReID: Surpassing Human-Level Performance in Person Re-Identificationcited by 61
- 2018Differentiable Learning-to-Normalize via Switchable Normalizationcited by 33
10 more
- 2019Hetero-Center Loss for Cross-Modality Person Re-Identificationcited by 30
- 2019Enhancing the Discriminative Feature Learning for Visible-Thermal Cross-Modality Person Re-Identificationcited by 16
- 2019HPILN: A feature learning framework for cross-modality person re-identificationcited by 13
- 2020Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identificationcited by 13
- 2020RGB-IR Cross-modality Person ReID based on Teacher-Student GAN Modelcited by 13
- 2019An Efficient Framework for Visible-Infrared Cross Modality Person Re-Identificationcited by 8
- 2021NAM: Normalization-based Attention Modulecited by 8
- 2020Strong but Simple Baseline with Dual-Granularity Triplet Loss for Visible-Thermal Person Re-Identificationcited by 7
- 2020Cross-Spectrum Dual-Subspace Pairing for RGB-infrared Cross-Modality Person Re-Identificationcited by 6
- 2022Cross-Modality Earth Mover's Distance for Visible Thermal Person Re-Identificationcited by 5
Built on by
Citing papers per year: 2023: 1.
1 paper.