Browse > Computer Vision > Activity Prediction > motion prediction

motion prediction

23 papers with code · Computer Vision
Subtask of Activity Prediction

Leaderboards

No evaluation results yet. Help compare methods by submit evaluation metrics.

Greatest papers with code

On human motion prediction using recurrent neural networks

CVPR 2017 facebookresearch/QuaterNet

Human motion modelling is a classical problem at the intersection of graphics and computer vision, with applications spanning human-computer interaction, motion synthesis, and motion prediction for virtual and augmented reality.

MOTION ESTIMATION MOTION PREDICTION

Tracking without bells and whistles

ICCV 2019 phil-bergmann/tracking_wo_bnw

We then perform an analysis on the performance and failure cases of several state-of-the-art tracking methods in comparison to our Tracktor.

MOTION COMPENSATION MOTION PREDICTION MULTI-OBJECT TRACKING

Animating Arbitrary Objects via Deep Motion Transfer

CVPR 2019 AliaksandrSiarohin/monkey-net

This is achieved through a deep architecture that decouples appearance and motion information.

IMAGE ANIMATION MOTION PREDICTION VIDEO GENERATION

Learning Trajectory Dependencies for Human Motion Prediction

ICCV 2019 wei-mao-2019/LearnTrajDep

In this paper, we propose a simple feed-forward deep network for motion prediction, which takes into account both temporal smoothness and spatial dependencies among human body joints.

HUMAN POSE FORECASTING MOTION CAPTURE MOTION PREDICTION

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

27 Nov 2017ebarsoum/hpgan

Our model, which we call HP-GAN, learns a probability density function of future human poses conditioned on previous poses.

AUTONOMOUS VEHICLES MOTION ESTIMATION MOTION PREDICTION

Integrating kinematics and environment context into deep inverse reinforcement learning for predicting off-road vehicle trajectories

16 Oct 2018yfzhang/vehicle-motion-forecasting

The first-stage network learns feature representations of the environment using low-level LiDAR statistics and the second-stage network combines those learned features with kinematics data.

AUTONOMOUS NAVIGATION MOTION PREDICTION TRAJECTORY PREDICTION

MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics

ECCV 2018 xcyan/eccv18_mtvae

Our model jointly learns a feature embedding for motion modes (that the motion sequence can be reconstructed from) and a feature transformation that represents the transition of one motion mode to the next motion mode.

HUMAN DYNAMICS MOTION PREDICTION

Structured Prediction Helps 3D Human Motion Modelling

ICCV 2019 eth-ait/spl

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.

MOTION FORECASTING MOTION PREDICTION STRUCTURED PREDICTION

ODE2VAE: Deep generative second order ODEs with Bayesian neural networks

NeurIPS 2019 cagatayyildiz/ODE2VAE

We present Ordinary Differential Equation Variational Auto-Encoder (ODE2VAE), a latent second order ODE model for high-dimensional sequential data.

IMPUTATION MOTION CAPTURE MOTION PREDICTION TIME SERIES