A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling
[article]
2019
arXiv
pre-print
Preserved Fulltext
It is also equipped with a new batch prediction model that predicts a large number of frames at once, such that long-term temporally-based objective functions can be employed to correctly learn the motion ...
Data-driven modeling of human motions is ubiquitous in computer graphics and computer vision applications, such as synthesizing realistic motions or recognizing actions. ...
The authors wish to gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research. ...
arXiv:1908.07214v1
fatcat:cbvk7xhpujeszcm6rapoqg2nzi
Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling
2019
IEEE Transactions on Visualization and Computer Graphics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
It is also equipped with a new batch prediction model that predicts a large number of frames at once, such that long-term temporally-based objective functions can be employed to correctly learn the motion ...
Data-driven modeling of human motions is ubiquitous in computer graphics and computer vision applications, such as synthesizing realistic motions or recognizing actions. ...
The authors wish to gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research. ...
doi:10.1109/tvcg.2019.2936810
pmid:31443030
fatcat:ul4scymsbzhh3a6cfg7lqw3erm
Learning Human Motion Models for Long-term Predictions
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We propose a new architecture for the learning of predictive spatio-temporal motion models from data alone. ...
Our approach, dubbed the Dropout Autoencoder LSTM, is capable of synthesizing natural looking motion sequences over long time horizons without catastrophic drift or motion degradation. ...
Integrating spatio-temporal information into algorithmic frameworks for motion prediction is hence either done via simple approximations such as optical flow [10, 27] or via manually designed and activity ...
arXiv:1704.02827v2
fatcat:ak3m3s7jprfcbdkcqcewstr4r4
Space-Time-Separable Graph Convolutional Network for Pose Forecasting
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
For the first time, STS-GCN models the human pose dynamics only with a graph convolutional network (GCN), including the temporal evolution and the spatial joint interaction within a single-graph framework ...
This has decoupled the two aspects and leveraged progress from the relevant fields, but it has also limited the understanding of the complex structural joint spatio-temporal dynamics of the human pose. ...
Acknowledgements The authors wish to acknowledge Panasonic for partially supporting this work and the project of the Italian Ministry of Education, Universities and Research (MIUR) "Dipartimenti di Eccellenza ...
arXiv:2110.04573v1
fatcat:ms2wf7xv5zcsrkmtucn2ggbox4
PERFORMANCE-DERIVED BEHAVIOR VOCABULARIES: DATA-DRIVEN ACQUISITION OF SKILLS FROM MOTION
2004
International Journal of Humanoid Robotics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf.
Second, we propose a datadriven method for deriving behavior vocabularies from time-series data of human motion using spatio-temporal dimension reduction and clustering. ...
First, we propose a representation for a skill-level interface as a "behavior vocabulary", a repertoire of modular exemplar-based memory models expressing kinematic motion. ...
The authors are grateful to Jessica Hodgins for human motion data, and Sarah R. Jenkins, Dylan Shell, Jon Eriksson, and Roger D. Sealion for insightful feedback. ...
doi:10.1142/s0219843604000186
fatcat:polj3gxsjfdgppchd2ziuzxt2q
Recurrent Network Models for Human Dynamics
[article]
2015
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
For video pose forecasting, ERD predicts body joint displacements across a temporal horizon of 400ms and outperforms a first order motion model based on optical flow. ...
We propose the Encoder-Recurrent-Decoder (ERD) model for recognition and prediction of human body pose in videos and motion capture. ...
Acknowledgements We would like to thank Jeff Donahue and Philipp Krähenbühl for useful discussions. We gratefully acknowledge NVIDIA corporation for the donation of K40 GPUs for this research. ...
arXiv:1508.00271v2
fatcat:w2me3ddf4fcfnmjf7yk55n5aje
Recurrent Network Models for Human Dynamics
2015
2015 IEEE International Conference on Computer Vision (ICCV)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
For video pose forecasting, ERD predicts body joint displacements across a temporal horizon of 400ms and outperforms a first order motion model based on optical flow. ...
We propose the Encoder-Recurrent-Decoder (ERD) model for recognition and prediction of human body pose in videos and motion capture. ...
Acknowledgements We would like to thank Jeff Donahue and Philipp Krähenbühl for useful discussions. We gratefully acknowledge NVIDIA corporation for the donation of K40 GPUs for this research. ...
doi:10.1109/iccv.2015.494
dblp:conf/iccv/FragkiadakiLFM15
fatcat:r2b2wbv2ordbneksnoji4ix2by
Human Motion Prediction via Spatio-Temporal Inpainting
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
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. ...
And finally, we argue that the L2 metric, considered so far by most approaches, fails to capture the actual distribution of long-term human motion. ...
This suggests that the relative motion generation is both harder for machine learning models and for humans. ...
arXiv:1812.05478v2
fatcat:bi7gt4wmnrgefgi72jg63ulcia
Human Motion Prediction via Spatio-Temporal Inpainting
2019
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
And finally, we argue that the L2 metric, considered so far by most approaches, fails to capture the actual distribution of long-term human motion. ...
We propose a Generative Adversarial Network (GAN) to forecast 3D human motion given a sequence of past 3D skeleton poses. ...
This suggests that the relative motion generation is both harder for machine learning models and for humans. ...
doi:10.1109/iccv.2019.00723
dblp:conf/iccv/RuizGM19
fatcat:rjaapq3f7vet5p4i56fhxrzmxa
Analyzing trajectories on Grassmann manifold for early emotion detection from depth videos
2015
2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
That is, a sequence of 3D faces is first split to an indexed collection of short-term sub-sequences that are represented as matrix (subspace) which define a special matrix manifold called, Grassmann manifold ...
In particular, we have studied the role of facial (shapes) dynamics in revealing the human identity and their exhibited spontaneous emotion. ...
For these reasons, our modeling of the temporal 95 evolution of human 3D faces is based on mapping the original 4D data to Grassmann 96 manifolds. ...
doi:10.1109/fg.2015.7163122
dblp:conf/fgr/AlashkarABD15
fatcat:53lkhk6apzaqndylmu5iphqupe
Convolutional Autoencoders for Human Motion Infilling
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper we propose a convolutional autoencoder to address the problem of motion infilling for 3D human motion data. ...
We demonstrate the versatility of the approach via a number of complex motion sequences and report on thorough evaluations performed to better understand the capabilities and limitations of the proposed ...
Acknowledgments We thank Janick Cardinale for his support. ...
arXiv:2010.11531v1
fatcat:5v5f5fimjfhdrhtcni7gixaimi
Human Motion Anticipation with Symbolic Label
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
This allows the model to anticipate motion changes many steps ahead and adapt the poses accordingly. We achieve state-of-the-art results on short-term as well as on long-term human motion forecasting. ...
In this work we approximate a person's intention via a symbolic representation, for example fine-grained action labels such as walking or sitting down. ...
Spatio-Temporal Motion Inpainting (STMI-GAN) [29] frames human motion anticipation as inpainting problem which can be solved using a GAN. ...
arXiv:1912.06079v2
fatcat:a7ihltc5s5fpzh36dbauk433gi
A Survey on Deep Learning for Skeleton-Based Human Animation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
First, we introduce motion data representations, most common human motion datasets and how basic deep models can be enhanced to foster learning of spatial and temporal patterns in motion data. ...
Second, we cover state-of-the-art approaches divided into three large families of applications in human animation pipelines: motion synthesis, character control and motion editing. ...
Acknowledgements This work was supported by the European Commission under European Horizon 2020 Programme, grant number 951911 -AI4Media.
Acronyms ...
arXiv:2110.06901v1
fatcat:abppln4rbbeufiw4z6a3wnk7oy
Convolutional Autoencoders for Human Motion Infilling
2020
2020 International Conference on 3D Vision (3DV)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We use a single model to generate motion for a wide range of activities, including locomotion, jumping, kicking, punching, and more. ...
We present a convolutional autoencoder architecture to fill in missing frames in 3D human motion data. ...
Acknowledgments We thank Janick Cardinale for his support. ...
doi:10.1109/3dv50981.2020.00102
fatcat:epllsnhahfhgdiavi5k2ze6xoq
Adversarial Geometry-Aware Human Motion Prediction
[chapter]
2018
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
than ours (3rd row, left) and error accumulates in long time horizons (3rd row, right) for residual sup. ...
Current approaches suffer from the problem of prediction discontinuities and may fail to predict human-like motion in longer time horizons due to error accumulation. ...
We also thank Deva Ramanan and Hongdong Li for valuable comments. ...
doi:10.1007/978-3-030-01225-0_48
fatcat:mwubi5o45rfitgk4i5swjiyt6e
« Previous
Showing results 1 — 15 out of 683 results