Learning with twin noisy labels for visible-infrared person re-identification

M Yang, Z Huang, P Hu, T Li, J Lv… - Proceedings of the …, 2022 - openaccess.thecvf.com
In this paper, we study an untouched problem in visible-infrared person re-identification (VI-
ReID), namely, Twin Noise Labels (TNL) which refers to as noisy annotation and …

Visible-infrared person re-identification via partially interactive collaboration

X Zheng, X Chen, X Lu - IEEE Transactions on Image …, 2022 - ieeexplore.ieee.org
Visible-infrared person re-identification (VI-ReID) task aims to retrieve the same person
between visible and infrared images. VI-ReID is challenging as the images captured by …

Hetero-center loss for cross-modality person re-identification

Y Zhu, Z Yang, L Wang, S Zhao, X Hu, D Tao - Neurocomputing, 2020 - Elsevier
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 …

Bi-directional exponential angular triplet loss for RGB-infrared person re-identification

H Ye, H Liu, F Meng, X Li - IEEE Transactions on Image …, 2020 - ieeexplore.ieee.org
RGB-Infrared person re-identification (RGB-IR Re-ID) is a cross-modality matching problem,
where the modality discrepancy is a big challenge. Most existing works use Euclidean metric …

Dual-semantic consistency learning for visible-infrared person re-identification

Y Zhang, Y Kang, S Zhao, J Shen - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Visible-Infrared person Re-Identification (VI-ReID) conducts comprehensive identity analysis
on non-overlapping visible and infrared camera sets for intelligent surveillance systems …

Learning to reduce dual-level discrepancy for infrared-visible person re-identification

Z Wang, Z Wang, Y Zheng… - Proceedings of the …, 2019 - openaccess.thecvf.com
Abstract Infrared-Visible person RE-IDentification (IV-REID) is a rising task. Compared to
conventional person re-identification (re-ID), IV-REID concerns the additional modality …

Hierarchical discriminative learning for visible thermal person re-identification

M Ye, X Lan, J Li, P Yuen - Proceedings of the AAAI conference on …, 2018 - ojs.aaai.org
Person re-identification is widely studied in visible spectrum, where all the person images
are captured by visible cameras. However, visible cameras may not capture valid …

Hierarchical temporal modeling with mutual distance matching for video based person re-identification

P Li, P Pan, P Liu, M Xu, Y Yang - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Comparing to image-based person re-identification (re-ID) problems, video-based person re-
ID can take advantage of more cues from appearance and temporal information, and …

Feature disentanglement learning with switching and aggregation for video-based person re-identification

M Kim, MA Cho, S Lee - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
In video person re-identification (Re-ID), the network must consistently extract features of the
target person from successive frames. Existing methods tend to focus only on how to use …

Dual-modality hard mining triplet-center loss for visible infrared person re-identification

X Cai, L Liu, L Zhu, H Zhang - Knowledge-Based Systems, 2021 - Elsevier
Visible infrared person re-identification (VI-reid) has gradually increased in popularity as an
crucial branch of person re-identification (reid). It not only has intra-class variations caused …