Filters








12,361 Hits in 6.2 sec

A Temporal Kernel-Based Model for Tracking Hand Movements from Neural Activities

Lavi Shpigelman, Koby Crammer, Rony Paz, Eilon Vaadia, Yoram Singer
2004 Neural Information Processing Systems  
We devise and experiment with a dynamical kernel-based system for tracking hand movements from neural activity.  ...  The system's state dynamics is defined as a combination of a linear mapping from the previous estimated state and a kernel-based mapping tailored for modeling neural activities.  ...  Introduction The paper focuses on the problem of tracking hand movements, which constitute smooth spatial trajectories, from spike trains of a neural population.  ... 
dblp:conf/nips/ShpigelmanCPVS04 fatcat:6a5qxya2pbdzfbiat64mmu6v4i

Generalised Structural CNNs (SCNNs) for time series data with arbitrary graph topology [article]

Thomas Teh, Chaiyawan Auepanwiriyakul, John Alexander Harston, A. Aldo Faisal
2018 arXiv   pre-print
Deep Learning methods, specifically convolutional neural networks (CNNs), have seen a lot of success in the domain of image-based data, where the data offers a clearly structured topology in the regular  ...  Therefore we define and implement here a framework for general graph-structured CNNs for time series analysis.  ...  of the prediction for the SCNN stems from the inclusion of the graph structure allowing the neural network to extract more meaningful representations of movement dynamics, allowing for a higher accuracy  ... 
arXiv:1803.05419v2 fatcat:jm5mrahnpnfhxe5fshdco72qsq

Neural Decoding Using Kernel-Based Functional Representation of ECoG Recordings [chapter]

S. García-Vega, A. M. Álvarez-Meza, Germán Castellanos-Domínguez
2014 Lecture Notes in Computer Science  
A Kernel-based Feature Representation (KFR) approach is proposed to extract patterns from multi-channel time-series of measured brain activity.  ...  Hence, the introduced KFR that seeks for spatio-temporal relationships among channels facilitates brain activity analysis relating to neural decoding tasks.  ...  This work is supported by the project "Sistemas de interacción cerebro -máquina (BMI) a partir de registros de actividad eléctrica cerebral", Programa Doctoral Becas COLCIENCIAS-Formación de alto nivel  ... 
doi:10.1007/978-3-319-12568-8_31 fatcat:zy6zoc2b3vftlnfa4gpw5jlrpm

Traffic Command Gesture Recognition for Virtual Urban Scenes Based on a Spatiotemporal Convolution Neural Network

Chunyong Ma, Yu Zhang, Anni Wang, Yuan Wang, Ge Chen
2018 ISPRS International Journal of Geo-Information  
Furthermore, a novel ST-CNN algorithm is presented that investigates a different architecture based on spatial and temporal convolution kernels.  ...  To actualize real-time traffic gesture recognition, a novel spatiotemporal convolution neural network (ST-CNN) model is presented.  ...  The features of the spatial dimension and the temporal dimension were extracted continuously by the movement of the convolution kernel. The ST-CNN model was thus established.  ... 
doi:10.3390/ijgi7010037 fatcat:kl7eyztxhfhi7g2wixw6hzvsty

Complex Deep Neural Networks from Large Scale Virtual IMU Data for Effective Human Activity Recognition Using Wearables

Hyeokhyen Kwon, Gregory D. Abowd, Thomas Plötz
2021 Sensors  
Our models contain components that are dedicated to capture the essentials of IMU data as they are of relevance for activity recognition, which increased the number of trainable parameters by a factor  ...  Supervised training of human activity recognition (HAR) systems based on body-worn inertial measurement units (IMUs) is often constrained by the typically rather small amounts of labeled sample data.  ...  Convolutional neural networks learn feature extraction kernels that capture local temporal patterns, which are then aggregated through multiple layers and in a hierarchical manner for effective data abstraction  ... 
doi:10.3390/s21248337 pmid:34960431 pmcid:PMC8707382 fatcat:ex27jvnfxnbq3g7b2wfdqmmy2a

Large-scale dynamics of perceptual decision information across human cortex

Niklas Wilming, Peter R. Murphy, Florent Meyniel, Tobias H. Donner
2020 Nature Communications  
We find such an endogenous component in early visual cortex (including V1), which is expressed in a low (<20 Hz) frequency band and tracks, with delay, the build-up of choice-predictive activity in (pre  ...  Perceptual decisions entail the accumulation of sensory evidence for a particular choice towards an action plan.  ...  Acknowledgements We thank Stanislas Dehaene, Mariano Sigman, and Genis Prat Ortega for discussion during this project, and Klaus Wimmer and Alan Stocker for thoughtful comments on the manuscript.  ... 
doi:10.1038/s41467-020-18826-6 pmid:33037209 fatcat:pxtdxj2nrrb4ph5azqz26jknrq

Long Jump Action Recognition Based on Deep Convolutional Neural Network

Zhiteng Wang, Jun Ye
2022 Computational Intelligence and Neuroscience  
From the perspective of rapid diagnostic feedback of students' long jump movements, we design and develop a long jump movement recognition method based on deep convolutional neural network.  ...  Long jump is a highly technical activity, which includes four basic movements: running aid, jumping, vacating, and landing.  ...  expanded by a factor of two for modeling a one-dimensional convolution with a temporal kernel size of 3 for the purpose of modeling temporal features [13] . e 2D convolutional interchannel fusion capability  ... 
doi:10.1155/2022/3832118 pmid:35676962 pmcid:PMC9168106 fatcat:ddffykfqx5dqlbo6zzfjxym4ga

Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions [article]

Alexandros Stergiou, Georgios Kapidis, Grigorios Kalliatakis, Christos Chrysoulas, Remco Veltkamp, Ronald Poppe
2019 arXiv   pre-print
for the signals that the network interpret as informative, is a challenging task.  ...  Because of the high level of complexity of these methods, as the convolution operations are also extended to additional dimension in order to extract features from them as well, providing a visualization  ...  , while we use the MFNet [26] from our previous example for spatio-temporal activations.  ... 
arXiv:1902.01078v2 fatcat:ejc7useqonbalb6fnozbv64nby

Score-level Multi Cue Fusion for Sign Language Recognition [article]

Çağrı Gökçe and Oğulcan Özdemir and Ahmet Alp Kındıroğlu and Lale Akarun
2020 arXiv   pre-print
We propose a more straightforward approach that focuses on training separate cue models specializing on the dominant hand, hands, face, and upper body regions.  ...  Furthermore, we include a discussion for fusion settings, which can help future work on Sign Language Translation (SLT).  ...  For the selected hand, track hand movements using Euclidean distance. Keep the frame ids of the start of the first-hand movement and end of the last hand-movement. 4.  ... 
arXiv:2009.14139v1 fatcat:khkejwatxzahpf765njcz2lnzq

Improving Finger Stroke Recognition Rate for Eyes-Free Mid-Air Typing in VR

Yatharth Singhal, Richard Huynh Noeske, Ayush Bhardwaj, Jin Ryong Kim
2022 CHI Conference on Human Factors in Computing Systems  
We examine mid-air typing data collected from touch typists to evaluate the features and classification models for recognizing finger stroke.  ...  Based on this analysis, we assess the performance of various classifiers, including Naive Bayes, Random Forest, Support Vector Machines, and Deep Neural Networks, in terms of the accuracy for correctly  ...  Supporting data for this publication is available at: https://mi-lab.io/data/in-airkeyboard-user-data.zip.  ... 
doi:10.1145/3491102.3502100 fatcat:2w7blyj2m5btnovszex7e6uhsa

Kernalised Multi-resolution Convnet for Visual Tracking [article]

Di Wu, Wenbin Zou, Xia Li, Yong Zhao
2017 arXiv   pre-print
Built upon their seminal work, there has been a plethora of recent improvements relying on convolutional neural network (CNN) pretrained on ImageNet as a feature extractor for visual tracking.  ...  Visual tracking is intrinsically a temporal problem. Discriminative Correlation Filters (DCF) have demonstrated excellent performance for high-speed generic visual object tracking.  ...  Acknowledgment This project has received funding from National Natural Science Foundation of China (NSFC) (61401287); Natural Science Foundation of Shenzhen (JCYJ20160307154003475, JCYJ2016050617265125  ... 
arXiv:1708.00577v1 fatcat:u6kz2j3yxrck5c2hlogdeqx4dy

Kernalised Multi-resolution Convnet for Visual Tracking

Di Wu, Wenbin Zou, Xia Li, Yong Zhao
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Built upon their seminal work, there has been a plethora of recent improvements relying on convolutional neural network (CNN) pretrained on ImageNet as a feature extractor for visual tracking.  ...  Visual tracking is intrinsically a temporal problem. Discriminative Correlation Filters (DCF) have demonstrated excellent performance for high-speed generic visual object tracking.  ...  Acknowledgment This project has received funding from National Natural Science Foundation of China (NSFC) (61401287); Natural Science Foundation of Shenzhen (JCYJ20160307154003475, JCYJ2016050617265125  ... 
doi:10.1109/cvprw.2017.278 dblp:conf/cvpr/WuZLZ17 fatcat:st46eaueuvf4xmmxhwyr2yoha4

Neural Network Related to Hand Movement: A Combined Study of Diffusion Tensor Tractography and Functional MRI

Ji Heon Hong, Sung Ho Jang
2011 Journal of Physical Therapy Science  
Probabilistic tractography was used to analyze diffusion tensor imaging (DTI) data that were collected using fMRI activation induced by grasp-release movements of the hand at a rate of 1 Hz.  ...  Purpose] Little is known about the detailed anatomical connections of the neural network related to hand movement in the human brain.  ...  Fiber tracking was performed using a probabilistic tractography method based on a multifiber model.  ... 
doi:10.1589/jpts.23.97 fatcat:34cri6c7rbcxzpn5kevko2pd5m

Disentangling Decision-related Feedforward and Feedback Signals in Human Cortex [article]

Niklas Wilming, Peter R Murphy, Florent Meyniel, Tobias Donner
2020 bioRxiv   pre-print
During perceptual decisions, agents accumulate sensory evidence for a particular choice towards an action plan.  ...  Our results challenge current, pure feedforward accounts of perceptual decision-making, and yield a computational interpretation of frequency-specific cortical oscillations.  ...  Acknowledgments We thank Stanislas Dehaene, Mariano Sigman, and Genis Prat Ortega for discussion during this project, and Klaus Wimmer and Alan Stocker for thoughtful comments on the manuscript.  ... 
doi:10.1101/2020.02.01.929893 fatcat:urx7dem4vfahliyvz54goxofym

Vision based Traffic Police Hand Signal Recognition in Surveillance Video - A Survey

R. Sathya, M. Kalaiselvi Geetha
2013 International Journal of Computer Applications  
The recognition of human hand gesture movement can be performed at various level of abstraction. This survey concentrate on approaches that aim on recognizing traffic police hand signals.  ...  Human gesture recognition has become a very important topic in computer vision. The purpose of this survey is to provide a detailed overview and categories of current issues and trends.  ...  Vision based hand gesture recognition is simple, natural and convenient for users. The active way is the better choice than the passive way.  ... 
doi:10.5120/14037-2192 fatcat:dtns3iu3fje77dnrgsn2346qoq
« Previous Showing results 1 — 15 out of 12,361 results