Beyond intra-modality: A survey of heterogeneous person re-identification
An efficient and effective person re-identification (ReID) system relieves the users from
painful and boring video watching and accelerates the process of video analysis. Recently …
painful and boring video watching and accelerates the process of video analysis. Recently …
Crdoco: Pixel-level domain transfer with cross-domain consistency
Unsupervised domain adaptation algorithms aim to transfer the knowledge learned from one
domain to another (eg, synthetic to real images). The adapted representations often do not …
domain to another (eg, synthetic to real images). The adapted representations often do not …
Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation
Person re-identification (re-ID) aims at recognizing the same person from images taken
across different cameras. To address this challenging task, existing re-ID models typically …
across different cameras. To address this challenging task, existing re-ID models typically …
Deep learning-based person re-identification methods: A survey and outlook of recent works
In recent years, with the increasing demand for public safety and the rapid development of
intelligent surveillance networks, person re-identification (Re-ID) has become one of the hot …
intelligent surveillance networks, person re-identification (Re-ID) has become one of the hot …
Deep high-resolution representation learning for cross-resolution person re-identification
G Zhang, Y Ge, Z Dong, H Wang… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Person re-identification (re-ID) tackles the problem of matching person images with the
same identity from different cameras. In practical applications, due to the differences in …
same identity from different cameras. In practical applications, due to the differences in …
A comprehensive overview of person re-identification approaches
H Wang, H Du, Y Zhao, J Yan - Ieee Access, 2020 - ieeexplore.ieee.org
Person re-identification, identifying and tracking pedestrians in cross-domain monitoring
systems, is an important technology in the computer vision field and of real significance for …
systems, is an important technology in the computer vision field and of real significance for …
Real-world person re-identification via degradation invariance learning
Person re-identification (Re-ID) in real-world scenarios usually suffers from various
degradation factors, eg, low-resolution, weak illumination, blurring and adverse weather. On …
degradation factors, eg, low-resolution, weak illumination, blurring and adverse weather. On …
Recover and identify: A generative dual model for cross-resolution person re-identification
Person re-identification (re-ID) aims at matching images of the same identity across camera
views. Due to varying distances between cameras and persons of interest, resolution …
views. Due to varying distances between cameras and persons of interest, resolution …
Towards generalizable person re-identification with a bi-stream generative model
Generalizable person re-identification (re-ID) has attracted growing attention due to its
powerful adaptation capability in the unseen data domain. However, existing solutions often …
powerful adaptation capability in the unseen data domain. However, existing solutions often …
Inter-task association critic for cross-resolution person re-identification
Person images captured by unconstrained surveillance cameras often have low resolutions
(LR). This causes the resolution mismatch problem when matched against the high …
(LR). This causes the resolution mismatch problem when matched against the high …