3D Human motion anticipation and classification

by   Emad Barsoum, et al.

Human motion prediction and understanding is a challenging problem. Due to the complex dynamic of human motion and the non-deterministic aspect of future prediction. We propose a novel sequence-to-sequence model for human motion prediction and feature learning, trained with a modified version of generative adversarial network, with a custom loss function that takes inspiration from human motion animation and can control the variation between multiple predicted motion from the same input poses. Our model learns to predict multiple future sequences of human poses from the same input sequence. We show that the discriminator learns general presentation of human motion by using the learned feature in action recognition task. Furthermore, to quantify the quality of the non-deterministic predictions, we simultaneously train a motion-quality-assessment network that learns the probability that a given sequence of poses is a real human motion or not. We test our model on two of the largest human pose datasets: NTURGB-D and Human3.6M. We train on both single and multiple action types. Its predictive power for motion estimation is demonstrated by generating multiple plausible futures from the same input and show the effect of each of the loss functions. Furthermore, we show that it takes less than half the number of epochs to train an activity recognition network by using the feature learned from the discriminator.


page 4

page 11


HP-GAN: Probabilistic 3D human motion prediction via GAN

Predicting and understanding human motion dynamics has many applications...

Deep representation learning for human motion prediction and classification

Generative models of 3D human motion are often restricted to a small num...

BiHMP-GAN: Bidirectional 3D Human Motion Prediction GAN

Human motion prediction model has applications in various fields of comp...

Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Prediction

Previous works on human motion prediction follow the pattern of building...

Simultaneous Action Recognition and Human Whole-Body Motion and Dynamics Prediction from Wearable Sensors

This paper presents a novel approach to solve simultaneously the problem...

Learning Variations in Human Motion via Mix-and-Match Perturbation

Human motion prediction is a stochastic process: Given an observed seque...

Adversarial training for predictive tasks: theoretical analysis and limitations in the deterministic case

To train a deep neural network to mimic the outcomes of processing seque...

Please sign up or login with your details

Forgot password? Click here to reset