Filters








19 Hits in 6.9 sec

Classification of sport videos using edge-based features and autoassociative neural network models

C. Krishna Mohan, B. Yegnanarayana
2008 Signal, Image and Video Processing  
The ability of autoassociative neural network (AANN) models to capture the distribution of feature vectors is exploited, to develop class-specific models using edge-based features.  ...  In this paper, we propose a method for classification of sport videos using edge-based features, namely edge direction histogram and edge intensity histogram.  ...  Appendix Autoassociative neural network models Autoassociative neural network models are feedforward neural networks performing an identity mapping of the input space, and are used to capture the distribution  ... 
doi:10.1007/s11760-008-0097-9 fatcat:cw4hsme4mvb25ay324pm2ya3lm

Audio-video based Segmentation and Classification using SVM and AANN

K. Subashini, S. Palanivel
2012 International Journal of Computer Applications  
Support vector machine(SVM) and autoassociative neural network(AANN) models are used for segmentation and classification.  ...  The classification system classify the audio-video data into one of the predefined categories such as news, advertisement, sports, serial and movies.  ...  The Support vector machine (SVM) and autoassociative neural network (AANN) models are used for modeling the features.  ... 
doi:10.5120/8525-2271 fatcat:dexnw5ljq5gsfmzr6qu6qqthjy

Video Classification and Shot Detection for Video Retrieval Applications

M. Kalaiselvi Geetha, S. Palanivel
2009 International Journal of Computational Intelligence Systems  
using autoassociative neural network (AANN) which makes retrieval problems much simpler.  ...  This paper proposes a new feature called Block Intensity Comparison Code (BICC) for video classification and an unsupervised shot change detection algorithm to detect the shot changes in a video stream  ...  Autoassociative neural network models are feedforward neural networks performing an identity mapping of the input space, and are used to capture the distribution of the input data8.  ... 
doi:10.1080/18756891.2009.9727638 fatcat:ai54x5rnvrbitc6aijogda5byy

Video Classification and Shot Detection for Video Retrieval Applications

M. K. Geetha, S. Palanivel
2009 International Journal of Computational Intelligence Systems  
using autoassociative neural network (AANN) which makes retrieval problems much simpler.  ...  This paper proposes a new feature called Block Intensity Comparison Code (BICC) for video classification and an unsupervised shot change detection algorithm to detect the shot changes in a video stream  ...  Autoassociative neural network models are feedforward neural networks performing an identity mapping of the input space, and are used to capture the distribution of the input data8.  ... 
doi:10.2991/jnmp.2009.2.1.5 fatcat:evhqeyea2bcw5es5b5rfyu7u7u

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

R. Sathya, M. Kalaiselvi Geetha
2013 International Journal of Computer Applications  
The purpose of this survey is to provide a detailed overview and categories of current issues and trends.  ...  Most of the recognition system uses the benchmark datasets like KTH, Weizmann. some other datasets were used by the action recognition system.  ...  A special kind of backpropagation neural network called Autoassociative Neural Network (AANN) [41] can be used to capture the distribution of feature vectors in the feature space.  ... 
doi:10.5120/14037-2192 fatcat:dtns3iu3fje77dnrgsn2346qoq

A literature review on one-class classification and its potential applications in big data

Naeem Seliya, Azadeh Abdollah Zadeh, Taghi M. Khoshgoftaar
2021 Journal of Big Data  
Under such conditions, modeling and detecting instances of the minority class is very difficult.  ...  , noisy data, feature selection, and data reduction.  ...  Acknowledgements We would like to thank the various reviewers in the Data Mining and Machine Learning Laboratory at Florida Atlantic University, Boca Raton, FL 33431.  ... 
doi:10.1186/s40537-021-00514-x fatcat:iaqfshjii5butmn64yrecd5yxq

Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances

Shibo Zhang, Yaxuan Li, Shen Zhang, Farzad Shahabi, Stephen Xia, Yu Deng, Nabil Alshurafa
2022 Sensors  
We also present cutting-edge frontiers and future directions for deep learning-based HAR.  ...  This paper systematically categorizes and summarizes existing work that introduces deep learning methods for wearables-based HAR and provides a comprehensive analysis of the current advancements, developing  ...  Acknowledgments: Special thanks to Haik Kalamtarian and Krystina Neuman for their valuable feedback. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s22041476 pmid:35214377 pmcid:PMC8879042 fatcat:vp6jssypezbd5cnyzn4g35eqrm

Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances [article]

Shibo Zhang, Yaxuan Li, Shen Zhang, Farzad Shahabi, Stephen Xia, Yu Deng, Nabil Alshurafa
2022 arXiv   pre-print
We also present cutting-edge frontiers and future directions for deep learning-based HAR.  ...  This paper systematically categorizes and summarizes existing work that introduces deep learning methods for wearables-based HAR and provides a comprehensive analysis of the current advancements, developing  ...  Acknowledgments Special thanks to Haik Kalamtarian and Krystina Neuman for their valuable feedback.  ... 
arXiv:2111.00418v5 fatcat:wylhzwkndjar7fc3esvhca2axi

Multi-grid cellular genetic algorithm for optimizing variable ordering of ROBDDs

Cristian Rotaru, Octav Brudaru
2012 2012 IEEE Congress on Evolutionary Computation  
The extensive experimental evaluation uses difficult classical benchmarks and proves the efficiency and the stability of the algorithm.  ...  Two feature functions are used to measure the similarity between chromosomes. The approach considers multiple parallel evolving grids.  ...  Okuno and Tetsuya Ogata, Self-organization of Object Features Representing Motion Using Multiple Timescales Recurrent Neural Network 393, Nopriadi Nopriadi and Yukihiko Yamashita, Extended Maximum a Posteriori-based  ... 
doi:10.1109/cec.2012.6256590 dblp:conf/cec/RotaruB12 fatcat:4ly3nrktw5habc6lf5err7d5py

Video browsing interfaces and applications: a review

Klaus Schoeffmann
2010 Journal of Photonics for Energy  
, and browsing solutions based on video surrogates.  ...  ., storage, retrieval, sharing) employing video data in the past decade, both for personal and professional use.  ...  The feature vectors are used as input for an anchorperson classifier working with autoassociative neural network models.  ... 
doi:10.1117/6.0000005 fatcat:xeanz3f6pnaizmtno4mumffhoq

Audio-video Geners Classification Using AANN

K Subashini
International Journal of Advanced Networking & Applications   unpublished
The results of audio and video confidence score are combined at each level(all six levels) using weighted sum rule for automatic audio-video based genres classification.  ...  Features used for categorizing audio are Mel frequency cepstral coefficients. Visual features are extracted using color histogram features in the video clips.  ...  MODELING TECHNIQUES USED FOR CLASSIFICATION a. Autoassociate Neural Network (AANN) Autoassociative neural network models are feed forward neural networks performing an identity mapping.  ... 
fatcat:ffu47r36nfdcnpl4fpiyxxjbji

Extraction of spatio-temporal primitives of emotional body expressions

Lars Omlor, Martin A. Giese
2007 Neurocomputing  
of guiding the neural network towards the edge of criticality.  ...  We are currently using AnimatLab to study the neural control of locomotion and the escape behavior of crayfish. High-speed video will be used to record the escape movements in 3D.  ... 
doi:10.1016/j.neucom.2006.10.100 fatcat:esivhljzsbcihdl5qbp756josu

Papers and Posters Presented at the 33rd Annual Meeting of the Psychonomic Society The Adams' Mark Hotel, St. Louis, Missouri November 13–15, 1992

1992 Bulletin of the Psychonomic Society  
Such latent inhibition for responding appears to dependon total amountof prior exposureto unrewarded leverpressing and is comparable to conventional latent inhibition using stimuliin several interesting  ...  These effects differ from those observed in adults and suggest an infantile disposition for configuring simultaneous compounds and encoding the net result amodally in terms of intensity. 8:35-8:45 (3)  ...  We modeled Michael Faraday 's experimentation by using a neural network to simulate the conduct and results of a series of experiments taken from his diary .  ... 
doi:10.3758/bf03334109 fatcat:5wkarsmzpbha5nlmx3pbut3kva

Low‐frequency pressure wave propagation in liquid‐filled, flexible tubes

Cato Bjelland, Leif Bjo/rno/
1992 Journal of the Acoustical Society of America  
Medwin and Daniel's (1990) measurements of the sound spectrum under gently spilling waves are shown to be consistent with a simple model of the acoustics based on the resonant relaxation of individual  ...  An analysis based on an acoustical model of the sensor yields the open-circuit sensitivity, which permits determination of the surface pressure levels.  ...  Several networks were investigated for detection and classification of the gearbox faults. The performance of each network will be presented.  ... 
doi:10.1121/1.403122 fatcat:x23kvbg555hpnktivjgqhvxspq

Multi-Modal Technology for User Interface Analysis including Mental State Detection and Eye Tracking Analysis

Ahmed Husseini Orabi, Université D'Ottawa / University Of Ottawa, Université D'Ottawa / University Of Ottawa
2017
The engine uses Deep Neural Networks to provide 1) a generative and probabilistic inference model, and 2) to handle multimodal data such that its performance does not degrade due to the absence of some  ...  The data sources our tool processes are nonintrusive, and captured from video; i.e. eye tracking, and facial expressions. For video data retrieval, we use a basic webcam.  ...  We use a deep multimodal neural network, to satisfy better denoising of data and reduction of an excessive number of features resulting from multiple modalities.  ... 
doi:10.20381/ruor-20731 fatcat:5ayqafaobzeavgxrcznn7n42q4
« Previous Showing results 1 — 15 out of 19 results