Breaking the Passive Learning Trap: An Active Perception Strategy for Human Motion Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Juncheng, Zhang, Zijian, Wang, Zeyu, Wang, Guoyu, Li, Yingji, Lyu, Kedi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917088632766464
author Hu, Juncheng
Zhang, Zijian
Wang, Zeyu
Wang, Guoyu
Li, Yingji
Lyu, Kedi
author_facet Hu, Juncheng
Zhang, Zijian
Wang, Zeyu
Wang, Guoyu
Li, Yingji
Lyu, Kedi
contents Forecasting 3D human motion is an important embodiment of fine-grained understanding and cognition of human behavior by artificial agents. Current approaches excessively rely on implicit network modeling of spatiotemporal relationships and motion characteristics, falling into the passive learning trap that results in redundant and monotonous 3D coordinate information acquisition while lacking actively guided explicit learning mechanisms. To overcome these issues, we propose an Active Perceptual Strategy (APS) for human motion prediction, leveraging quotient space representations to explicitly encode motion properties while introducing auxiliary learning objectives to strengthen spatio-temporal modeling. Specifically, we first design a data perception module that projects poses into the quotient space, decoupling motion geometry from coordinate redundancy. By jointly encoding tangent vectors and Grassmann projections, this module simultaneously achieves geometric dimension reduction, semantic decoupling, and dynamic constraint enforcement for effective motion pose characterization. Furthermore, we introduce a network perception module that actively learns spatio-temporal dependencies through restorative learning. This module deliberately masks specific joints or injects noise to construct auxiliary supervision signals. A dedicated auxiliary learning network is designed to actively adapt and learn from perturbed information. Notably, APS is model agnostic and can be integrated with different prediction models to enhance active perceptual. The experimental results demonstrate that our method achieves the new state-of-the-art, outperforming existing methods by large margins: 16.3% on H3.6M, 13.9% on CMU Mocap, and 10.1% on 3DPW.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14237
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Breaking the Passive Learning Trap: An Active Perception Strategy for Human Motion Prediction
Hu, Juncheng
Zhang, Zijian
Wang, Zeyu
Wang, Guoyu
Li, Yingji
Lyu, Kedi
Computer Vision and Pattern Recognition
Forecasting 3D human motion is an important embodiment of fine-grained understanding and cognition of human behavior by artificial agents. Current approaches excessively rely on implicit network modeling of spatiotemporal relationships and motion characteristics, falling into the passive learning trap that results in redundant and monotonous 3D coordinate information acquisition while lacking actively guided explicit learning mechanisms. To overcome these issues, we propose an Active Perceptual Strategy (APS) for human motion prediction, leveraging quotient space representations to explicitly encode motion properties while introducing auxiliary learning objectives to strengthen spatio-temporal modeling. Specifically, we first design a data perception module that projects poses into the quotient space, decoupling motion geometry from coordinate redundancy. By jointly encoding tangent vectors and Grassmann projections, this module simultaneously achieves geometric dimension reduction, semantic decoupling, and dynamic constraint enforcement for effective motion pose characterization. Furthermore, we introduce a network perception module that actively learns spatio-temporal dependencies through restorative learning. This module deliberately masks specific joints or injects noise to construct auxiliary supervision signals. A dedicated auxiliary learning network is designed to actively adapt and learn from perturbed information. Notably, APS is model agnostic and can be integrated with different prediction models to enhance active perceptual. The experimental results demonstrate that our method achieves the new state-of-the-art, outperforming existing methods by large margins: 16.3% on H3.6M, 13.9% on CMU Mocap, and 10.1% on 3DPW.
title Breaking the Passive Learning Trap: An Active Perception Strategy for Human Motion Prediction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.14237