Paper Info
Title
Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction
Abstract
Predicting human motion from historical pose sequence is crucial for a machine to succeed in intelligent interactions with humans. One aspect that has been obviated so far, is the fact that how we represent the skeletal pose has a critical impact on the prediction results. Yet there is no effort that investigates across different pose representation schemes. We conduct an indepth study on various pose representations with a focus on their effects on the motion prediction task. Moreover, recent approaches build upon off-the-shelf RNN units for motion prediction. These approaches process input pose sequence sequentially and inherently have difficulties in capturing long-term dependencies. In this paper, we propose a novel RNN architecture termed AHMR (Attentive Hierarchical Motion Recurrent network) for motion prediction which simultaneously models local motion contexts and a global context. We further explore a geodesic loss and a forward kinematics loss for the motion prediction task, which have more geometric significance than the widely employed L2 loss. Interestingly, we applied our method to a range of articulate objects including human, fish, and mouse. Empirical results show that our approach outperforms the state-of-the-art methods in short-term prediction and achieves much enhanced long-term prediction proficiency, such as retaining natural human-like motions over 50 seconds predictions. Our codes are released.
Year
DOI
Venue
2023
10.1109/TPAMI.2021.3139918
IEEE Transactions on Pattern Analysis and Machine Intelligence
Keywords
DocType
Volume
Motion prediction,motion context,recurrent neural network,kinematic chain,pose representation
Journal
45
Issue
ISSN
Citations 
1
0162-8828
1
PageRank 
References 
Authors
0.35
0
7
Name
Order
Citations
PageRank
Zhenguang Liu110.68
Shuang Wu212.04
Shuyuan Jin340.74
Shouling Ji461656.91
Qi Liu510.35
Shijian Lu6134693.57
Li Cheng751833.34