A Neural Temporal Model for Human Motion Prediction

@article{Gopalakrishnan2019ANT,
  title={A Neural Temporal Model for Human Motion Prediction},
  author={Anand Gopalakrishnan and Ankur Mali and Daniel Kifer and C. Lee Giles and Alexander Ororbia},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={12108-12117}
}
We propose novel neural temporal models for predicting and synthesizing human motion, achieving state-of-the-art in modeling long-term motion trajectories while being competitive with prior work in short-term prediction and requiring significantly less computation. [...] Key Method Key aspects of our proposed system include: 1) a novel, two-level processing architecture that aids in generating planned trajectories, 2) a simple set of easily computable features that integrate derivative information, and 3) a…Expand
PVRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction
TLDR
A novel Position-Velocity Recurrent Encoder-Decoder (PVRED) for human motion prediction, which makes full use of pose velocities and temporal positional information and considerably outperforms the state-of-the-art methods.
AGVNet: Attention Guided Velocity Learning for 3D Human Motion Prediction
TLDR
A novel attention-guided velocity learning network, AGVNet, that utilizes multi-order information such as positions and velocities derived from the dynamic states of the human body for predicting human motion.
Multi-level Motion Attention for Human Motion Prediction
TLDR
This work proposes to extract motion attention to capture the similarity between the current motion context and the historical motion sub-sequences to effectively exploit motion patterns from the long-term history to predict the future poses.
Few-shot Human Motion Prediction via Learning Novel Motion Dynamics
TLDR
This work proposes a novel approach named Motion Prediction Network (MoPredNet) for few-short human motion prediction that can be adapted to predicting new motion dynamics using limited data, and it elegantly captures long-term dependency in motion dynamics.
Intention-based Long-Term Human Motion Anticipation
Recently, a few works have been proposed to model the uncertainty of the future human motion. These works do not forecast a single sequence but multiple sequences for the same observation. While
History Repeats Itself: Human Motion Prediction via Motion Attention
TLDR
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.
Motion Prediction using Trajectory Cues
Predicting human motion from a historical pose sequence is at the core of many applications in computer vision. Current state-of-the-art methods concentrate on learning motion contexts in the pose
Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks
  • Chunzhi Gu, Yan Zhao, Chao Zhang
  • Computer Science
    ArXiv
  • 2021
TLDR
A novel approach to predict future human motions from a much weaker condition, i.e., a single image, with mixture density networks (MDN) modeling, and introduces an energybased prior over learnable parameters of MDN to maintain motion coherence, as well as improve the prediction accuracy.
Human Motion Prediction Via Pattern Completion in Latent Representation Space
TLDR
A novel and general approach to solve human motion understanding via pattern completion on a learned latent representation space based on sequence-to-sequence learning that outperforms current state-of-the-art methods in human motion prediction across a number of tasks, with no customization.
Unsupervised and Generic Short-Term Anticipation of Human Body Motions
TLDR
This work proposes to use Dynamic Mode Decomposition with delays to represent and anticipate human body motions as linear combinations of previous states and delays and shows that the anticipation errors in the results are comparable to or even better for very short anticipation times than a recurrent neural network based method.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 41 REFERENCES
On Human Motion Prediction Using Recurrent Neural Networks
TLDR
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.
Learning Human Motion Models for Long-Term Predictions
TLDR
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.
Recurrent Network Models for Human Dynamics
TLDR
The Encoder-Recurrent-Decoder (ERD) model is a recurrent neural network that incorporates nonlinear encoder and decoder networks before and after recurrent layers that extends previous Long Short Term Memory models in the literature to jointly learn representations and their dynamics.
Auto-Conditioned Recurrent Networks for Extended Complex Human Motion Synthesis
TLDR
This work is the first to the knowledge that demonstrates the ability to generate over 18,000 continuous frames (300 seconds) of new complex human motion w.r.t. different styles.
Learning Switching Linear Models of Human Motion
TLDR
A new variational inference algorithm is obtained by casting the SLDS model as a Dynamic Bayesian Network, and classification experiments show the superiority of SLDS over conventional HMM's for the problem domain.
Gaussian Process Dynamical Models for Human Motion
TLDR
This work marginalize out the model parameters in closed form by using Gaussian process priors for both the dynamical and the observation mappings, which results in a nonparametric model for dynamical systems that accounts for uncertainty in the model.
Modeling Human Motion Using Binary Latent Variables
TLDR
A non-linear generative model for human motion data that uses an undirected model with binary latent variables and real-valued "visible" variables that represent joint angles that makes on-line inference efficient and allows for a simple approximate learning procedure.
Implicit Probabilistic Models of Human Motion for Synthesis and Tracking
TLDR
A low dimensional linear model of human motion is learned that is used to structure the example motion database into a binary tree and an approximate probabilistic tree search method exploits the coefficients of this low-dimensional representation and runs in sub-linear time.
Structural-RNN: Deep Learning on Spatio-Temporal Graphs
TLDR
This paper develops a scalable method for casting an arbitrary spatio-temporal graph as a rich RNN mixture that is feedforward, fully differentiable, and jointly trainable and shows improvement over the state-of-the-art with a large margin.
Learning Simpler Language Models with the Differential State Framework
TLDR
The delta-RNN outperforms popular complex architectures, such as the long short-term memory (LSTM) and the gated recurrent unit (GRU), and, when regularized, performs comparably to several state-of-the-art baselines.
...
1
2
3
4
5
...