• Corpus ID: 228063941

Long Term Motion Prediction Using Keyposes

  title={Long Term Motion Prediction Using Keyposes},
  author={Sena Kiciroglu and Wei Wang and Mathieu Salzmann and P. Fua},
Long term human motion prediction is an essential component in safety-critical applications, such as human-robot interaction and autonomous driving. We argue that, to achieve long term forecasting, predicting human pose at every time instant is unnecessary because human motion follows patterns that are well-represented by a few essential poses in the sequence. We call such poses "keyposes", and approximate complex motions by linearly interpolating between subsequent keyposes. We show that… 

3D Pose Based Feedback for Physical Exercises

A learning-based framework that identifies the mistakes made by a user and proposes corrective measures for easier and safer individual training, which uses a Graph Convolutional Network architecture acting on the user’s pose sequence to model the relationship between the the body joints trajectories.



Anticipating Many Futures: Online Human Motion Prediction and Generation for Human-Robot Interaction

This work presents a conditional variational autoencoder that is trained to predict awindow of future human motion given a window of past frames, and investigates how movements and kinematic cues are represented on the learned low dimensional manifold.

A Stochastic Conditioning Scheme for Diverse Human Motion Prediction

This paper proposes to stochastically combine the root of variations with previous pose information, so as to force the model to take the noise into account, and exploits this idea for motion prediction by incorporating it into a recurrent encoder-decoder network with a conditional variational autoencoder block that learns to exploit the perturbations.

Context-Aware Human Motion Prediction

This paper uses a semantic-graph model where the nodes parameterize the human and objects in the scene and the edges their mutual interactions, and learns a context-aware motion prediction architecture that outperforms baselines in which the context information is not considered.

Learning Trajectory Dependencies for Human Motion Prediction

A simple feed-forward deep network for motion prediction, which takes into account both temporal smoothness and spatial dependencies among human body joints, and design a new graph convolutional network to learn graph connectivity automatically.

On Human Motion Prediction Using Recurrent Neural Networks

It is shown that, surprisingly, state of the art performance can be achieved by a simple baseline that does not attempt to model motion at all, and a simple and scalable RNN architecture is proposed that obtains state-of-the-art performance on human motion prediction.

History Repeats Itself: Human Motion Prediction via Motion Attention

An attention-based feed-forward network is introduced that explicitly leverages the observation that human motion tends to repeat itself to capture motion attention to capture the similarity between the current motion context and the historical motion sub-sequences.

Teaching Robots to Predict Human Motion

A motion GAN model is introduced that achieves superior prediction performance to state-of-the-art approaches when evaluated on the standard H3.6M dataset and demonstrates its ability to replay the predicted motion in a human-like manner when interacting with a person.

Motion Prediction Using Temporal Inception Module

A Temporal Inception Module (TIM) to encode human motion is proposed, making use of TIM, and the framework produces input embeddings using convolutional layers, by using different kernel sizes for different input lengths.

Learning Human Motion Models for Long-Term Predictions

The Dropout Autoencoder LSTM (DAELSTM), a new architecture for the learning of predictive spatio-temporal motion models from data alone, is capable of synthesizing natural looking motion sequences over long-time horizons without catastrophic drift or motion degradation.

Imitation Learning for Human Pose Prediction

This paper proposes a new reinforcement learning formulation for the problem of human pose prediction, and develops an imitation learning algorithm for predicting future poses under this formulation through a combination of behavioral cloning and generative adversarial imitation learning.