Complementary attention-driven contrastive learning with hard-sample exploring for unsupervised domain adaptive person re-id
Unsupervised domain adaptive (UDA) methods for person re-identification (Re-ID) aim to
transfer the knowledge of the labeled source domain to the unlabeled target domain without …
transfer the knowledge of the labeled source domain to the unlabeled target domain without …
Exploring Frontier Technologies in Video-Based Person Re-Identification: A Survey on Deep Learning Approach.
Video-based person re-identification (Re-ID), a subset of retrieval tasks, faces challenges
like uncoordinated sample capturing, viewpoint variations, occlusions, cluttered …
like uncoordinated sample capturing, viewpoint variations, occlusions, cluttered …
Learning diverse and deep clues for person reidentification
W Qin, B Huang, P Qin, Z Huang, D Zhong - Image and Vision Computing, 2022 - Elsevier
Extracting robust features has been the core of person re-identification (ReID). The existing
convolutional neural network-based methods pay more attention to local features rather than …
convolutional neural network-based methods pay more attention to local features rather than …
Cross-Modal Distillation for RGB-Depth Person Re-Identification
Person re-identification is a key challenge for surveillance across multiple sensors.
Prompted by the advent of powerful deep learning models for visual recognition, and …
Prompted by the advent of powerful deep learning models for visual recognition, and …
STCA: Utilizing a spatio-temporal cross-attention network for enhancing video person re-identification
Video-based re-identification (ReID) is a crucial task in computer vision that draws
increasing attention due to advances in deep learning (DL) and modern computational …
increasing attention due to advances in deep learning (DL) and modern computational …
Deep learning for video-based person re-identification: A survey
K Islam - arxiv preprint arxiv:2303.11332, 2023 - arxiv.org
Video-based person re-identification (video re-ID) has lately fascinated growing attention
due to its broad practical applications in various areas, such as surveillance, smart city, and …
due to its broad practical applications in various areas, such as surveillance, smart city, and …
Cross-modal distillation for RGB-depth person re-identification
Person re-identification is a key challenge for surveillance across multiple sensors.
Prompted by the advent of powerful deep learning models for visual recognition, and …
Prompted by the advent of powerful deep learning models for visual recognition, and …
Spatial-temporal aware network for video-based person re-identification
J Wang, Q Zhao, D Jia, Z Huang, M Zhang… - Multimedia Tools and …, 2024 - Springer
Video-based pedestrian re-identification (ReID) is able to match the same pedestrian from
various cameras in a complex real-world scene. The extracted representations can't contain …
various cameras in a complex real-world scene. The extracted representations can't contain …
Cross-Modal Synergies: Unveiling the Potential of Motion-Aware Fusion Networks in Handling Dynamic and Static ReID Scenarios
F Ling, H Liu, G Huang, J Li, H Wu, Z Tang - arxiv preprint arxiv …, 2025 - arxiv.org
Navigating the complexities of person re-identification (ReID) in varied surveillance
scenarios, particularly when occlusions occur, poses significant challenges. We introduce …
scenarios, particularly when occlusions occur, poses significant challenges. We introduce …
Rethink Motion Information for Occluded Person Re-Identification
H Liu, X Chen - Applied Sciences, 2024 - mdpi.com
Person re-identification aims to identify the same pedestrians captured by various cameras
from different viewpoints in multiple scenarios. Occlusion is the toughest problem for …
from different viewpoints in multiple scenarios. Occlusion is the toughest problem for …