RGB-Infrared Cross-Modality Person Re-identification

By Ancong Wu, Weishi Zheng, Hong-Xing Yu, Shaogang Gong, J. Lai. IEEE International Conference on Computer Vision, 2017

796 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4060f7d9f58afd5b0e0e9f94e4838f5267e61ff0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Infrared-Visible Cross-Modal Person Re-Identification with an X Modality (2020, methodology): “The first two listed in Table 1 are introduced at length in (Wu et al. 2017), which are the modifications of the widely used IDE method (Zheng, Yang, and Hauptmann 2016) under IV-ReID protocol.”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, background): “Wu et al. [20] start the ﬁrst attempt to address this issue, by proposing a deep zero-padding framework [20] to adaptively learn the modality sharable features.”
RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment (2019, methodology): “(1) SYSU- MM01 [32] is a popular RGB-IR Re-ID dataset, which includes 491 identities from 4 RGB cameras and 2 IR ones.”
Bi-Directional Center-Constrained Top-Ranking for Visible Thermal Person Re-Identification (2020, methodology): “Therefore, their methods usually have limited performance for VT-REID [11].”
Cross-Modality Person Re-Identification with Generative Adversarial Training (2018, methodology): “Very recently, the work in [Wu et al. , 2017] introduces a cross-modality RGB-IR dataset named SYSU RGB-IR Re-ID, as shown in Fig.1.”
Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification (2020, methodology): “[50] introduced a zero-padding strategy with a one-stream network for cross-modality feature representation learning.”
FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification (2018, background): “Person reID [22, 23, 24, 25, 26, 27, 28, 29] is a challenging task due to various human poses, domain differences, occlusions, etc .”
Learning to Reduce Dual-Level Discrepancy for Infrared-Visible Person Re-Identification (2019, methodology): “As for the SYSU-MM01 dataset, the gallery consists of visible images, the results go the other way round.”
Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification (2019, methodology): “For these conditions, most surveillance cameras automatically switch from visible to the infrared mode in dark environments [33, 34].”
Channel Augmented Joint Learning for Visible-Infrared Recognition (2021, methodology): “Both models are trained under the same setting on the visible-infrared person re-identification dataset, SYSU-MM01 [42].”
Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer (2020, methodology): “In this subsection, we compare our proposed algorithm with the baselines as well as the state-of-the-art methods, including Zero-Padding [46], TONE [49], BDTR [50], cm-GAN [4], D 2 RL[44], MSR[7], D-HSME[13], IPVT[19], JSIA-ReID[57] and AlignGAN[42].”
Deep Multimodal Data Fusion (2024, neutral): “…Face Anti Proofing RGB + Thermal CASIA-SURF [230], CASIA-SURF Cefa [102] Speakingfaces [1], ThermalFace [8], TTVF [63], UL-FMTV [52], Person Re-Identification RGB+Thermal RegDB [131], SYSU-MM01 [196], BIWI RGBD-ID [127], RGBD-ID [13], SUCVL RGBD-ID [120], RobotPKU [105], KinectREID [135] task.”
Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification (2020, methodology): “(Wu et al. 2017; Ye et al. 2018a; 2018b; Dai et al. 2018; Hao et al. 2019) try to reduce the marginal distribution divergence between RGB and IR modalities, while cannot deal with their joint distributions.”
Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark (2021, result): “Similar views can be found in cross-modality person reidentification [50, 51].”
Style Normalization and Restitution for Generalizable Person Re-Identification (2020, methodology): “To further demonstrate the capability of SNR in handling images with large style variations, we conduct experiment on a more challenging RGB-Infrared cross-modality person ReID task on benchmark dataset SYSU-MM01 [46].”