Corpus ID: 237266730

Classifying In-Place Gestures with End-to-End Point Cloud Learning

  title={Classifying In-Place Gestures with End-to-End Point Cloud Learning},
  author={Lizhi Zhao and Xuequan Lu and Min Zhao and Meili Wang},
Walking in place for moving through virtual environments has attracted noticeable attention recently. Recent attempts focused on training a classifier to recognize certain patterns of gestures (e.g., standing, walking, etc) with the use of neural networks like CNN or LSTM. Nevertheless, they often consider very few types of gestures and/or induce less desired latency in virtual environments. In this paper, we propose a novel framework for accurate and efficient classification of in-place… Expand

Figures and Tables from this paper


DeepGRU: Deep Gesture Recognition Utility
DeepGRU, a novel end-to-end deep network model informed by recent developments in deep learning for gesture and action recognition, that is streamlined and device-agnostic, and yet achieves state-of-the-art results on challenging datasets is proposed. Expand
Accurate and Fast Classification of Foot Gestures for Virtual Locomotion
A novel method, Dual-Check Till Consensus, is proposed to reduce the latency of gesture recognition from 2 seconds to 0.5 seconds and increase the accuracy to over 97%. Expand
Gestures as point clouds: a $P recognizer for user interface prototypes
P, a new member of the $-family, that remedies this limitation by considering gestures as clouds of points by delivering >99% accuracy in user-dependent testing with 5+ training samples per gesture type and stays above 99% for user-independent tests when using data from 10 participants. Expand
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
A hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set and proposes novel set learning layers to adaptively combine features from multiple scales to learn deep point set features efficiently and robustly. Expand
PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation
A novel 3D Domain Adaptation Network for point cloud data (PointDAN) is proposed, which jointly aligns the global and local features in multi-level and demonstrates the superiority of the model over the state-of-the-art general-purpose DA methods. Expand
Predicting the Torso Direction from HMD Movements for Walk-in-Place Navigation through Deep Learning
While preliminary, the results show the possible inter-dependence between the viewing and torso directions, and with richer dataset and more parameters, a more accurate level of prediction seems possible. Expand
Improving Walking in Place Methods with Individualization and Deep Networks
A new, fast method for individualizing the walking in place algorithm based on biomechanic measures of step rate is provided and an adequately trained convolutional neural network can be an effective way of implementing walk in place. Expand
SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
This work introduces a new model SqueezeSegV2, which is more robust against dropout noises in LiDAR point cloud and therefore achieves significant accuracy improvement, and a domain-adaptation training pipeline consisting of three major components: learned intensity rendering, geodesic correlation alignment, and progressive domain calibration. Expand
Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
A generic deep framework for activity recognition based on convolutional and LSTM recurrent units, which is suitable for multimodal wearable sensors, does not require expert knowledge in designing features, and explicitly models the temporal dynamics of feature activations is proposed. Expand
Dynamic Graph CNN for Learning on Point Clouds
This work proposes a new neural network module suitable for CNN-based high-level tasks on point clouds, including classification and segmentation called EdgeConv, which acts on graphs dynamically computed in each layer of the network. Expand