Filters








163,617 Hits in 5.1 sec

Pitch and time, tonality and meter: How do musical dimensions combine?

Jon B. Prince, William F. Thompson, Mark A. Schmuckler
2009 Journal of Experimental Psychology: Human Perception and Performance  
The combinations of values along these two dimensions (pitch-time events) may influence how they combine perceptually.  ...  Experiments 1 and 2 collected ratings of goodness of fit for probe events that combined different pitch classes and temporal positions, whereas Experiments 3 and 4 used a speeded classification of either  ... 
doi:10.1037/a0016456 pmid:19803659 fatcat:t7ew4p6puvd6hp3cxxjkjsaziu

Contamination Event Detection Method Using Multi-Stations Temporal-Spatial Information Based on Bayesian Network in Water Distribution Systems

Jie Yu, Le Xu, Xiang Xie, Dibo Hou, Pingjie Huang, Guangxin Zhang, Hongjian Zhang
2017 Water  
In this paper, a contamination event detection method is proposed, in which both temporal and spatial information from multi-stations in water distribution systems are used.  ...  Results indicate that the proposed method shows higher accuracy due to its increased information from both temporal and spatial dimensions.  ...  The founding sponsors had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, and in the decision to publish the results.  ... 
doi:10.3390/w9110894 fatcat:6ivezolfbngzzkafkzde4lonmu

SPATIOTEMPORAL ORGANIZATION OF ENERGY RELEASE EVENTS IN THE QUIET SOLAR CORONA

Vadim M. Uritsky, Joseph M. Davila
2014 Astrophysical Journal  
Using data from STEREO and SOHO spacecraft, we show that temporal organization of energy release events in the quiet solar corona is close to random, in contrast to the clustered behavior of flaring times  ...  The locations of the quiet-Sun events follow the meso- and supergranulation pattern of the underling photosphere.  ...  Our detection method [32] [33] [34] identifies image features staying for more than one sampling interval above a specified detection threshold and occupying separable connected subvolumes in the three-dimensional  ... 
doi:10.1088/0004-637x/795/1/15 fatcat:hwprzv54rrftjgzy6b3t5tkqpa

EigenEvent: An algorithm for event detection from complex data streams in syndromic surveillance

Hadi Fanaee-T, João Gama
2015 Intelligent Data Analysis  
The type of data that is being generated via these systems is usually multivariate and seasonal with spatial and temporal dimensions.  ...  The algorithm What's Strange About Recent Events (WSARE) is the state-of-the-art method for such problems.  ...  Spatiotemporal methods instead take into account both spatial and temporal dimensions.  ... 
doi:10.3233/ida-150734 fatcat:hibrpp3zpnemtfs5igfqouj75e

Study of Human Action Recognition Based on Improved Spatio-temporal Features

Xiao-Fei Ji, Qian-Qian Wu, Zhao-Jie Ju, Yang-Yang Wang
2014 International Journal of Automation and Computing  
The proposed method detects interest points by using an improved interest points detection method.  ...  By combining local spatio-temporal feature and global positional distribution information (PDI) of interest points,a novel motion descriptor is proposed in this paper.  ...  First step, an improved detecting method [22] is used to detect spatiotemporal interest points, different from Dollar's method, effectively avoiding the error detecting in the background.  ... 
doi:10.1007/s11633-014-0831-4 fatcat:xjqpxu4j3nhj7o7qikbaq7jzme

Robust Event Detection based on Spatio-Temporal Latent Action Unit using Skeletal Information [article]

Hao Xing, Yuxuan Xue, Mingchuan Zhou, Darius Burschka
2021 arXiv   pre-print
The event action is represented as several latent atoms and composed of latent spatial and temporal attributes. We perform the method at the example of fall event detection.  ...  Our approach achieves the bestperformance on precision and accuracy of human fall event detection, compared with other existing dictionary learning methods.  ...  ACKNOWLEDGMENT We gratefully acknowledge the funding of the Lighthouse Initiative Geriatronics by StMWi Bayern (Project X, grant no. 5140951) and LongLeif GaPa GmbH (Project Y, grant no. 5140953).  ... 
arXiv:2109.02376v2 fatcat:djhmsbs32jadhlaczhl2oprb3q

A Novel Action Recognition Method Based on Improved Spatio-Temporal Features and AdaBoost-SVM Classifiers

Xiaofei Ji, Lu Zhou, Qianqian Wu
2015 International Journal of Hybrid Information Technology  
An improved spatio-temporal is proposed in this paper by combining local spatio-temporal feature and global positional distribution information (FEA) of interest points.  ...  The test results verified the proposed representation and recognition method can more accurately describe and recognize the human motion.  ...  Her research is focus on the human action modeling and recognition. She has published 3 research papers in this research direction.  ... 
doi:10.14257/ijhit.2015.8.5.19 fatcat:b2r5lxwfsfethbzrcp3q4bafxa

Assessment of Self-Attention on Learned Features For Sound Event Localization and Detection [article]

Parthasaarathy Sudarsanam, Archontis Politis, Konstantinos Drossos
2021 arXiv   pre-print
Joint sound event localization and detection (SELD) is an emerging audio signal processing task adding spatial dimensions to acoustic scene analysis and sound event detection.  ...  We studied the influence of stacking multiple self-attention blocks, using multiple attention heads in each self-attention block, and the effect of position embeddings and layer normalization.  ...  Drossos has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 957337, project MARVEL.  ... 
arXiv:2107.09388v2 fatcat:pnb5b3f6jzfrho6bu7lgydatia

Assessment of Self-Attention on Learned Features For Sound Event Localization and Detection

Parthasaarathy Sudarsanam, Archontis Politis, Konstantinos Drossos
2021 Zenodo  
Joint sound event localization and detection (SELD) is an emerging audio signal processing task adding spatial dimensions to acoustic scene analysis and sound event detection.  ...  We studied the influence of stacking multiple self-attention blocks, using multiple attention heads in each self-attention block, and the effect of position embeddings and layer normalization.  ...  Drossos has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 957337, project MARVEL.  ... 
doi:10.5281/zenodo.5723115 fatcat:mzigd3kg5bgkrlzzd4kodhs5we

Robust and Interpretable Temporal Convolution Network for Event Detection in Lung Sound Recordings [article]

Tharindu Fernando, Sridha Sridharan, Simon Denman, Houman Ghaemmaghami, Clinton Fookes
2021 arXiv   pre-print
framework for lung sound event detection.  ...  This paper proposes a novel framework for lung sound event detection, segmenting continuous lung sound recordings into discrete events and performing recognition on each event.  ...  The utility of these methods, and the potential diagnostic outcomes, can be improved by temporally localising the events within the lung sound recordings [2] , which we refer to as "lung sound event detection  ... 
arXiv:2106.15835v1 fatcat:lwsht3575jf3ppoy2pg6olrnli

Event detection in consumer videos using GMM supervectors and SVMs

Yusuke Kamishima, Nakamasa Inoue, Koichi Shinoda
2013 EURASIP Journal on Image and Video Processing  
We devised a multimedia event detection method based on Gaussian mixture model (GMM) supervectors and support vector machines.  ...  By combining these methods with the existing features, we aim to construct a high-performance event detection system. The effectiveness of our method is evaluated using TRECVID MED task benchmark.  ...  Such spatial-temporal features were introduced to event detection in [6, 8] , and they improved the detection rate when combined with visual and audio features.  ... 
doi:10.1186/1687-5281-2013-51 fatcat:4qtdrvj3ofcc5mgqlnfeexdyl4

Pattern and Anomaly Detection in Urban Temporal Networks [article]

Mingyi He, Shivam Pathak, Urwa Muaz, Jingtian Zhou, Saloni Saini, Sergey Malinchik, Stanislav Sobolevsky
2019 arXiv   pre-print
Abrupt changes in urban dynamics caused by events such as disruption of civic operations, mass crowd gatherings, holidays and natural disasters are potentially reflected in these temporal mobility networks  ...  Anomaly detection from high dimensional network data is a challenging task as edge level measurements often have low values and high variance resulting in high noise-to-signal ratio.  ...  In this section we discuss the methods that deal with event detection in temporal networks and are closely related to individual components in our pipeline.  ... 
arXiv:1912.01960v1 fatcat:usao7arw75d25l3aexbitfep44

Transient motion classification through turbid volumes via parallelized single-photon detection and deep contrastive embedding [article]

Shiqi Xu, Wenhui Liu, Xi Yang, Joakim Jönsson, Ruobing Qian, Paul McKee, Kanghyun Kim, Pavan Chandra Konda, Kevin C. Zhou, Lucas Kreiß, Haoqian Wang, Edouard Berrocal (+2 others)
2022 arXiv   pre-print
Fast noninvasive probing of spatially varying decorrelating events, such as cerebral blood flow beneath the human skull, is an essential task in various scientific and clinical settings.  ...  Along with a deep contrastive learning algorithm that outperforms classic unsupervised learning methods, we demonstrate our approach can accurately detect and classify different transient decorrelation  ...  RESULTS We created three datasets as a first validation of our new method, to evaluate the performance in separating spatial, temporal, and spatio-temporal varying decorrelating events.  ... 
arXiv:2204.01733v1 fatcat:so2gkae3cbf5hhlxaekqm247lu

weg2vec: Event embedding for temporal networks

Maddalena Torricelli, Márton Karsai, Laetitia Gauvin
2020 Scientific Reports  
Here, we propose a new method of event embedding of temporal networks, called weg2vec, which builds on temporal and structural similarities of events to learn a low dimensional representation of a temporal  ...  Temporal networks may provide an advantage in the description of real systems, but they code more complex information, which could be effectively represented only by a handful of methods so far.  ...  MK and LG acknowledge support from the IXXI Complex System Institute. MK has been supported by the ACADEMICS (IDEX Lyon) and by the DataRedux ANR (ANR-19-CE46-0008) projects.  ... 
doi:10.1038/s41598-020-63221-2 pmid:32346033 fatcat:r5ymgckdojghpoizlg7ylh6dqy

An Approach to Representing Movement Data

Hong Nguyen
2013 International Journal of Information and Electronics Engineering  
The movement of an object is represented by the change of its position through space and the change of its attributes over time or location.  ...  Several authors used two cubes to represent a moving object, one for spatio-temporal positions and another for attributes changing over location.  ...  An ungiven route mode is a combination of two Cartesian coordinate systems, a 2-dimension coordinate system and a 3-dimension coordinate system.  ... 
doi:10.7763/ijiee.2013.v3.318 fatcat:irvao2u37vd6fmc453cuxgkusi
« Previous Showing results 1 — 15 out of 163,617 results