Learning motion manifolds with convolutional autoencoders

By Daniel Holden, Jun Saito, Taku Komura, Thomas Joyce. SIGGRAPH Asia Technical Briefs, 2015

311 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/a64016af6a565d5078c8c56ce373202721dcc1e0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

A Gentle Introduction to Deep Learning in Medical Image Processing (2018, background): “Variants use convolutional networks [42], add noise to the input [43], or aim at finding sparse representations [44].”
A Review of the Evolution of Vision-Based Motion Analysis and the Integration of Advanced Computer Vision Methods Towards Developing a Markerless System (2018, methodology): “To ensure only physically realistic solutions are produced, the algorithms must be supported by constraints on the body model such as explicit joint limits [80] or probabilistic spaces of human pose and motion deduced by machine learning [81].”
Artificial intelligence in the creative industries: a review (2020, methodology): “These motion characteristics can be learnt using DL-based approaches, such as autoencoders [47], LSTMs [53], and motion prediction networks [48].”
AI Choreographer: Music Conditioned 3D Dance Generation with AIST++ (2021, background): “…many approaches explore the applicability of neural networks to generate 3D motion by training on a large-scale motion capture dataset, where network architectures such as CNNs [35, 34], GANs [31], RBMs [80], RNNs [24, 4, 40, 27, 16, 18, 88, 12, 87] and Transform-ers [3, 9] have been explored.”
Phase-functioned neural networks for character control (2017, methodology): “Previously some success has been achieved using convolutional models such as CNNs [Holden et al. 2016, 2015], autoregressive models such as RBMs [Taylor and Hinton 2009], and RNNs [Fragkiadaki et al. 2015].”
QuaterNet: A Quaternion-based Recurrent Model for Human Motion (2018, methodology): “For the latter, we use the same dataset as [22, 23], instead of Human3.”
A Spatio-temporal Transformer for 3D Human Motion Prediction (2020, methodology): “In [14, 15] convolutional models are introduced for motion synthesis”
Mode-adaptive neural networks for quadruped motion control (2018, background): “Forthecharacter animation purpose, Holden et al. [2015] use convolutional neural network (CNN) and learn temporal filters as the representation of motions.”
iLGaCo: Incremental Learning of Gait Covariate Factors (2020, methodology): “[14] designed a CNN to correct wrong human skeletons obtained either from research methods or real devices (e.”