Semi-Supervised Unconstrained Head Pose Estimation in the Wild
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-03 · 48 (3) · 3082-3099
DOI: 10.1109/tpami.2025.3631642 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-03. Verfasst von Huayi Zhou und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Head, Image Processing, Computer-Assisted, Posture, Supervised Machine Learning. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 114 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shanghai Municipal Science and Technology Major Project, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Existing research on unconstrained in-the-wild head pose estimation suffers from the flaws of its datasets, which consist of either numerous samples by non-realistic synthesis or constrained collection, or small-scale natural images yet with plausible manual annotations. This makes fully-supervised solutions compromised due to the reliance on generous labels. To alleviate it, we propose the first semi-supervised unconstrained head pose estimation method SemiUHPE, which can leverage abundant easily available unlabeled head images. Technically, we choose semi-supervised rotation regression and adapt it to the error-sensitive and label-scarce problem of unconstrained head pose. Our method is based on the observation that the aspect-ratio invariant cropping of wild heads is superior to previous landmark-based affine alignment given that landmarks of unconstrained human heads are usually unavailable, especially for underexplored non-frontal heads. Instead of using a pre-fixed threshold to filter out pseudo labeled heads, we propose dynamic entropy based filtering to adaptively remove unlabeled outliers as training progresses by updating the threshold in multiple stages. We then revisit the design of weak-strong augmentations and improve it by devising two novel head-oriented strong augmentations, termed pose-irrelevant cut-occlusion and pose-altering rotation consistency respectively. Extensive experiments and ablation studies show that SemiUHPE outperforms its counterparts greatly on public benchmarks under both the front-range and full-range settings. Furthermore, our proposed method is also beneficial for solving other closely related problems, including generic object rotation regression and 3D head reconstruction, demonstrating good versatility and extensibility.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Natural Science Foundation of China
- Shanghai Municipal Science and Technology Major Project
- Fundamental Research Funds for the Central Universities
- Guangdong S&T Programme
Zitieren
APA
Zhou, H., Jiang, F., Yuan, J., Rui, Y., Lu, H., & Jia, K. (2026). Semi-Supervised Unconstrained Head Pose Estimation in the Wild. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(3), 3082-3099. https://doi.org/10.1109/tpami.2025.3631642
Vancouver
Zhou H, Jiang F, Yuan J, Rui Y, Lu H, Jia K. Semi-Supervised Unconstrained Head Pose Estimation in the Wild. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(3):3082-3099. doi:10.1109/tpami.2025.3631642
BibTeX
@article{Zhou2026,
author = {Zhou, Huayi and Jiang, Fei and Yuan, Jin and Rui, Yong and Lu, Hongtao and Jia, Kui},
title = {Semi-Supervised Unconstrained Head Pose Estimation in the Wild},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {3},
pages = {3082--3099},
doi = {10.1109/tpami.2025.3631642}
}
EUVIMED