Action-Agnostic Human Pose Forecasting

23 Oct 2018  ·  Hsu-kuang Chiu, Ehsan Adeli, Borui Wang, De-An Huang, Juan Carlos Niebles ·

Predicting and forecasting human dynamics is a very interesting but challenging task with several prospective applications in robotics, health-care, etc. Recently, several methods have been developed for human pose forecasting; however, they often introduce a number of limitations in their settings. For instance, previous work either focused only on short-term or long-term predictions, while sacrificing one or the other. Furthermore, they included the activity labels as part of the training process, and require them at testing time. These limitations confine the usage of pose forecasting models for real-world applications, as often there are no activity-related annotations for testing scenarios. In this paper, we propose a new action-agnostic method for short- and long-term human pose forecasting. To this end, we propose a new recurrent neural network for modeling the hierarchical and multi-scale characteristics of the human dynamics, denoted by triangular-prism RNN (TP-RNN). Our model captures the latent hierarchical structure embedded in temporal human pose sequences by encoding the temporal dependencies with different time-scales. For evaluation, we run an extensive set of experiments on Human 3.6M and Penn Action datasets and show that our method outperforms baseline and state-of-the-art methods quantitatively and qualitatively. Codes are available at

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Human Pose Forecasting Human3.6M TP-RNN MAR, walking, 400ms 0.65 # 4
MAR, walking, 1,000ms 0.77 # 3


No methods listed for this paper. Add relevant methods here