Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-05 · 46 (5) · 3595-3607
DOI: 10.1109/tpami.2023.3346168 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-05. Verfasst von Min Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 74 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Supervised person re-identification (re-id) methods require expensive manual labeling costs. Although unsupervised re-id methods can reduce the requirement of the labeled datasets, the performance of these methods is lower than the supervised alternatives. Recently, some weakly supervised learning-based person re-id methods have been proposed, which is a balance between supervised and unsupervised learning. Nevertheless, most of these models require another auxiliary fully supervised datasets or ignore the interference of noisy tracklets. To address this problem, in this work, we formulate a weakly supervised tracklet association learning (WS-TAL) model only leveraging the video labels. Specifically, we first propose an intra-bag tracklet discrimination learning (ITDL) term. It can capture the associations between person identities and images by assigning pseudo labels to each person image in a bag. And then, the discriminative feature for each person is learned by utilizing the obtained associations after filtering the noisy tracklets. Based on that, a cross-bag tracklet association learning (CTAL) term is presented to explore the potential tracklet associations between bags by mining reliable positive tracklet pairs and hard negative pairs. Finally, these two complementary terms are jointly optimized to train our re-id model. Extensive experiments on the weakly labeled datasets demonstrate that WS-TAL achieves 88.1% and 90.3% rank-1 accuracy on the MARS and DukeMTMC-VideoReID datasets respectively. The performance of our model surpasses the state-of-the-art weakly supervised models by a large margin, even outperforms some fully supervised re-id models.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Liu, M., Bian, Y., Liu, Q., Wang, X., & Wang, Y. (2024). Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(5), 3595-3607. https://doi.org/10.1109/tpami.2023.3346168
Vancouver
Liu M, Bian Y, Liu Q, Wang X, Wang Y. Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(5):3595-3607. doi:10.1109/tpami.2023.3346168
BibTeX
@article{Liu2024,
author = {Liu, Min and Bian, Yuan and Liu, Qing and Wang, Xueping and Wang, Yaonan},
title = {Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {5},
pages = {3595--3607},
doi = {10.1109/tpami.2023.3346168}
}
EUVIMED