Meta-Auxiliary Learning for Adaptive Human Pose Prediction


  • Qiongjie Cui Nanjing University of Science and Technology
  • Huaijiang Sun Nanjing University of Science and Technology
  • Jianfeng Lu Nanjing University of Science and Technology
  • Bin Li Tianjin AiForward Science and Technology Co., Ltd., China
  • Weiqing Li Nanjing University of Science and Technology



ROB: Human-Robot Interaction, CV: 3D Computer Vision, HAI: Human-Aware Planning and Behavior Prediction


Predicting high-fidelity future human poses, from a historically observed sequence, is crucial for intelligent robots to interact with humans. Deep end-to-end learning approaches, which typically train a generic pre-trained model on external datasets and then directly apply it to all test samples, emerge as the dominant solution to solve this issue. Despite encouraging progress, they remain non-optimal, as the unique properties (e.g., motion style, rhythm) of a specific sequence cannot be adapted. More generally, once encountering out-of-distributions, the predicted poses tend to be unreliable. Motivated by this observation, we propose a novel test-time adaptation framework that leverages two self-supervised auxiliary tasks to help the primary forecasting network adapt to the test sequence. In the testing phase, our model can adjust the model parameters by several gradient updates to improve the generation quality. However, due to catastrophic forgetting, both auxiliary tasks typically have a low ability to automatically present the desired positive incentives for the final prediction performance. For this reason, we also propose a meta-auxiliary learning scheme for better adaptation. Extensive experiments show that the proposed approach achieves higher accuracy and more realistic visualization.




How to Cite

Cui, Q., Sun, H., Lu, J., Li, B., & Li, W. (2023). Meta-Auxiliary Learning for Adaptive Human Pose Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 37(5), 6166-6174.



AAAI Technical Track on Intelligent Robotics