Representing motion as a sequence of latent primitives, a flexible approach for human motion modelling (original) (raw)
Related papers
Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling
IEEE Transactions on Visualization and Computer Graphics
LARNet: Latent Action Representation for Human Action Synthesis
2021
GlocalNet: Class-aware Long-term Human Motion Synthesis
2021 IEEE Winter Conference on Applications of Computer Vision (WACV), 2021
MoVi: A large multi-purpose human motion and video dataset
PLOS ONE, 2021
Hierarchical Graph-Convolutional Variational AutoEncoding for Generative Modelling of Human Motion
ArXiv, 2021
Generative Model-Enhanced Human Motion Prediction
ArXiv, 2020
Lecture Notes in Computer Science, 2012
Efficient movement representation by embedding Dynamic Movement Primitives in deep autoencoders
2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids), 2015
Pose Transformers (POTR): Human Motion Prediction with Non-Autoregressive Transformers
2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021
Flow-based Autoregressive Structured Prediction of Human Motion
2021
Deep Video Generation, Prediction and Completion of Human Action Sequences
Computer Vision – ECCV 2018, 2018
Multi-frame sequence generator of 4D human body motion
2021
Learning Trajectory Dependencies for Human Motion Prediction
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Learning Variations in Human Motion via Mix-and-Match Perturbation
2019
Learning Spatio-temporal Characteristics of Human Motions Through Observation
michail Maniadakis, Maria Koskinopoulou
International Conference on Robotics in Alpe-Adria Danube Region RAAD 2018: Advances in Service and Industrial Robotics pp 82-90, 2018
A Causal Convolutional Neural Network for Motion Modeling and Synthesis
2021
Sequence-to-Sequence Modeling for Action Identification at High Temporal Resolution
ArXiv, 2021
Human Motion Synthesis by Motion Manifold Learning and Motion Primitive Segmentation
Lecture Notes in Computer Science, 2006
On Human Motion Prediction Using Recurrent Neural Networks
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
Deep Generative Modelling of Human Reach-and-Place Action
ArXiv, 2020
PEEK - An LSTM Recurrent Network for Motion Classification from Sparse Data
Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2018
Learning Self-Similarity in Space and Time as Generalized Motion for Action Recognition
arXiv (Cornell University), 2021
ViLPAct: A Benchmark for Compositional Generalization on Multimodal Human Activities
arXiv (Cornell University), 2022
Modeling human motion using manifold learning and factorized generative models
2007
Self-supervised representation learning for long-complex activities using multiple modalities
2020
H4D: Human 4D Modeling by Learning Neural Compositional Representation
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space
Proceedings of the 30th ACM International Conference on Multimedia
Deep Representation Learning of 3D Human Motionwith Recurrent Neural Networks
2021
A Body Part Embedding Model With Datasets for Measuring 2D Human Motion Similarity
IEEE Access, 2021
Convolutional Learning of Spatio-temporal Features
Lecture Notes in Computer Science, 2010
ActionFlowNet: Learning Motion Representation for Action Recognition
2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 2018
Development of human motion prediction strategy using inception residual block
Multimedia Tools and Applications
Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition
2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021
Enriching a motion database by analogous combination of partial human motions
The Visual Computer, 2008
Dynamical Deep Generative Latent Modeling of 3D Skeletal Motion
International Journal of Computer Vision