Patent
Deep-learning motion priors for full-body performance capture in real-time
TLDR
In this paper, a physics-based tracking framework is proposed to train motion priors using different deep learning techniques, such as convolutional neural networks (CNN) and Recurrent Temporal Restricted Boltzmann Machines (RTRBMs).Abstract:
Training data from multiple types of sensors and captured in previous capture sessions can be fused within a physics-based tracking framework to train motion priors using different deep learning techniques, such as convolutional neural networks (CNN) and Recurrent Temporal Restricted Boltzmann Machines (RTRBMs). In embodiments employing one or more CNNs, two streams of filters can be used. In those embodiments, one stream of the filters can be used to learn the temporal information and the other stream of the filters can be used to learn spatial information. In embodiments employing one or more RTRBMs, all visible nodes of the RTRBMs can be clamped with values obtained from the training data or data synthesized from the training data. In cases where sensor data is unavailable, the input nodes may be unclamped and the one or more RTRBMs can generate the missing sensor data.read more
Citations
More filters
Proceedings ArticleDOI
Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation
Jose Caballero,Christian Ledig,Andrew Peter Aitken,Alejandro Acosta,Johannes Totz,Zehan Wang,Wenzhe Shi +6 more
TL;DR: In this article, a spatio-temporal sub-pixel convolution network is proposed to exploit temporal redundancies and improve reconstruction accuracy while maintaining real-time speed, and a novel joint motion compensation and video super-resolution algorithm that is orders of magnitude more efficient than competing methods.
Patent
An improved CNN-based aerial handwritten motion recognition
TL;DR: In this article, an improved air handwriting action recognition method of a convolution neural network was proposed, which uses CNN of a multi-time series and a partial weight sharing technology, and solves the shortcomings of the traditional method that features need to be designed manually and the like.
Patent
human-human interaction behavior identification method based on a lightweight convolutional neural network
TL;DR: In this article, a human-human interaction behavior identification method based on a lightweight convolutional neural network was proposed, and the two-person interaction behavior image set was constructed.
Patent
Neural network circuit and self-circulation multi-stage iteration method thereof
Liao Yumin,Wen Yongjie +1 more
TL;DR: In this article, a neural network circuit consisting of an image reduction unit, a sensitive area image data reading unit and a multi-channel selection unit, was proposed for classification and recognition, and a continuously refined recognition result was obtained through going deep for multiple turns.
Patent
Automated activity-time training
TL;DR: In this paper, the authors automatically train an actor upon the occurrence of a physical condition with respect to that actor, based on the actor's physical condition, such as engaging in or about to engage in a physical activity.
References
More filters
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Journal ArticleDOI
Reducing the Dimensionality of Data with Neural Networks
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.
Journal ArticleDOI
A fast learning algorithm for deep belief nets
TL;DR: A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
Proceedings Article
Two-Stream Convolutional Networks for Action Recognition in Videos
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work proposes a two-stream ConvNet architecture which incorporates spatial and temporal networks and demonstrates that a ConvNet trained on multi-frame dense optical flow is able to achieve very good performance in spite of limited training data.
Journal ArticleDOI
Neocognitron: A Self Organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position
TL;DR: A neural network model for a mechanism of visual pattern recognition that is self-organized by “learning without a teacher”, and acquires an ability to recognize stimulus patterns based on the geometrical similarity of their shapes without affected by their positions.