Human Motion Prediction via Continual Prior Compensation
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026
DOI: 10.1109/tpami.2026.3651530 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026. Verfasst von Jianwei Tang und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Pattern Recognition, Automated. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Natural Science Funds, Guangdong NSF for Distinguished Young Scholar.
Abstract (Originalsprache)
Human Motion Prediction (HMP) aims to predict future human poses at different moments according to observed past motion sequences. Previous approaches mainly treated the prediction of different temporal moments as a single prediction task and learned the predictions of varied moments simultaneously, which would encounter a main limitation: the learning of short-term predictions (referring to "near-future" prediction) could be hindered by the predictions of long-term (referring to "far-future" prediction) motions. In this paper, we develop a novel temporal continual learning framework called Continual Prior Compensation (CPC) to progressively train HMP models, in which we divide the prediction task of motions corresponding to varied temporal moments into several subtasks and train the model in a multi-stage manner. To mitigate the prior information forgetting in the progressive training, we further introduce a learnable random variable Prior Compensation Factor (PCF) to explicitly measure the prior knowledge loss. We theoretically show that the PCF can be efficiently learned together with the model parameters by minimizing a reasonable upper bound of the objective function. The proposed CPC is further enhanced to estimate the prior information loss for each subtask and a new framework called Continual Prior Compensation++ (CPC++) with Fine-Grained Prior Compensation Factor (FGPCF) is finally developed. Our CPC and CPC++ frameworks are quite flexible and can be easily integrated with different HMP backbone models and adapted to various datasets and applications. Extensive experiments on three HMP benchmark datasets using multiple SOTA HMP backbones (PGBIG, siMLPe, MotionMixer, and LTD) demonstrate the effectiveness and flexibility of our frameworks.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Natural Science Foundation of China
- Guangdong Natural Science Funds
- Guangdong NSF for Distinguished Young Scholar
- Guangdong Provincial Key Laboratory of Information Security Technology
Zitieren
APA
Tang, J., Hu, J. F., Liang, T., Lin, X., Sun, J., Zheng, W. S., & Lai, J. (2026). Human Motion Prediction via Continual Prior Compensation. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/tpami.2026.3651530
Vancouver
Tang J, Hu JF, Liang T, Lin X, Sun J, Zheng WS, et al. Human Motion Prediction via Continual Prior Compensation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026. doi:10.1109/tpami.2026.3651530
BibTeX
@article{Tang2026,
author = {Tang, Jianwei and Hu, Jian-Fang and Liang, Tianming and Lin, Xiaotong and Sun, Jiangxin and Zheng, Wei-Shi and Lai, Jianhuang},
title = {Human Motion Prediction via Continual Prior Compensation},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
doi = {10.1109/tpami.2026.3651530}
}
EUVIMED