Human motion prediction
59 papers with code • 0 benchmarks • 4 datasets
Action prediction is a pre-fact video understanding task, which focuses on future states, in other words, it needs to reason about future states or infer action labels before the end of action execution.
Benchmarks
These leaderboards are used to track progress in Human motion prediction
EMDB
GTA-IM Dataset
VIENA2
Most implemented papers
A Neural Temporal Model for Human Motion Prediction
cr7anand/neural_temporal_models
•
•
CVPR 2019
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.
Human Motion Prediction via Spatio-Temporal Inpainting
magnux/MotionGAN
•
•
First, we represent the data using a spatio-temporal tensor of 3D skeleton coordinates which allows formulating the prediction problem as an inpainting one, for which GANs work particularly well.
Human Motion Prediction via Learning Local Structure Representations and Temporal Dependencies
CHELSEA234/SkelNet_motion_prediction
•
•
Skel-TNet consists of three components: SkelNet and a Recurrent Neural Network, they have advantages in learning spatial and temporal dependencies for predicting human motion, respectively; a feed-forward network that outputs the final estimation.
Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs
amiryanj/socialways
•
•
CVPR 2019
We show through experiments on real and synthetic data that the proposed method leads to generate more diverse samples and to preserve the modes of the predictive distribution.
PVRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction
We therefore propose a novel Position-Velocity Recurrent Encoder-Decoder (PVRED) for human motion prediction, which makes full use of pose velocities and temporal positional information.
Human Motion Prediction via Spatio-Temporal Inpainting
magnux/MotionGAN
•
•
ICCV 2019
First, we represent the data using a spatio-temporal tensor of 3D skeleton coordinates which allows formulating the prediction problem as an inpainting one, for which GANs work particularly well.
Structured Prediction Helps 3D Human Motion Modelling
eth-ait/spl
•
•
ICCV 2019
This is implemented via a hierarchy of small-sized neural networks connected analogously to the kinematic chains in the human body as well as a joint-wise decomposition in the loss function.
The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction
JunweiLiang/Multiverse
•
•
CVPR 2020
The first contribution is a new dataset, created in a realistic 3D simulator, which is based on real world trajectory data, and then extrapolated by human annotators to achieve different latent goals.
Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction
limaosen0/DMGNN
•
•
The core idea of DMGNN is to use a multiscale graph to comprehensively model the internal relations of a human body for motion feature learning.
DLow: Diversifying Latent Flows for Diverse Human Motion Prediction
Khrylx/DLow
•
•
ECCV 2020
To obtain samples from a pretrained generative model, most existing generative human motion prediction methods draw a set of independent Gaussian latent codes and convert them to motion samples.
