TY - JOUR
T1 - CSFRNet
T2 - Integrating Clothing Status Awareness for Long-Term Person Re-identification
AU - Huang, Yan
AU - Huang, Yan
AU - Zhang, Zhang
AU - Wu, Qiang
AU - Zhong, Yi
AU - Wang, Liang
N1 - Publisher Copyright:
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.
PY - 2025
Y1 - 2025
N2 - Addressing the dynamic nature of long-term person re-identification (LT-reID) amid varying clothing conditions necessitates a departure from conventional methods. Traditional LT-reID strategies, mainly biometrics-based and data adaptation-based, each have their pitfalls. The former falters in environments lacking high-quality biometric data, while the latter loses efficacy with minimal or subtle clothing changes. To overcome these obstacles, we propose the clothing status-aware feature regularization network (CSFRNet). This novel approach seamlessly incorporates clothing status awareness into the feature learning process, significantly enhancing the adaptability and accuracy of LT-reID systems where clothing can either change completely, partially, or not at all over time, without the need for explicit clothing labels. The versatility of our CSFRNet is showcased on diverse LT-reID benchmarks, including Celeb-reID, Celeb-reID-light, PRCC, DeepChange, and LTCC, marking a significant advancement in the field by addressing the real-world variability of clothing in LT-reID scenarios.
AB - Addressing the dynamic nature of long-term person re-identification (LT-reID) amid varying clothing conditions necessitates a departure from conventional methods. Traditional LT-reID strategies, mainly biometrics-based and data adaptation-based, each have their pitfalls. The former falters in environments lacking high-quality biometric data, while the latter loses efficacy with minimal or subtle clothing changes. To overcome these obstacles, we propose the clothing status-aware feature regularization network (CSFRNet). This novel approach seamlessly incorporates clothing status awareness into the feature learning process, significantly enhancing the adaptability and accuracy of LT-reID systems where clothing can either change completely, partially, or not at all over time, without the need for explicit clothing labels. The versatility of our CSFRNet is showcased on diverse LT-reID benchmarks, including Celeb-reID, Celeb-reID-light, PRCC, DeepChange, and LTCC, marking a significant advancement in the field by addressing the real-world variability of clothing in LT-reID scenarios.
KW - Clothing status awareness
KW - Feature regularization
KW - Long-term person re-identification
UR - http://www.scopus.com/inward/record.url?scp=85213709884&partnerID=8YFLogxK
U2 - 10.1007/s11263-024-02315-0
DO - 10.1007/s11263-024-02315-0
M3 - Article
AN - SCOPUS:85213709884
SN - 0920-5691
JO - International Journal of Computer Vision
JF - International Journal of Computer Vision
ER -