Filters








117,336 Hits in 4.7 sec

Motion estimation using statistical learning theory

H. Wechsler, Z. Duric, F. Li, V. Cherkassky
2004 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This paper describes a novel application of Statistical Learning Theory (SLT) to single motion estimation and tracking.  ...  The problem of motion estimation can be related to statistical model selection, where the goal is to select one (correct) motion model from several possible motion models, given finite noisy samples.  ...  Cherkassky was supported, in part, by the US National Science Foundation grant ECS-0099906.  ... 
doi:10.1109/tpami.2004.1265862 pmid:15382651 fatcat:mcav3fpzpbf2hd5qgxip6zcp4y

Neuroimaging: Into the Multiverse [article]

Jessica Dafflon, Pedro F. Da Costa, František Váša, Ricardo Pio Monti, Danilo Bzdok, Peter J. Hellyer, Federico Turkheimer, Jonathan Smallwood, Emily Jones, Robert Leech
2020 bioRxiv   pre-print
Examples of possible choices include the motion regression approach used and smoothing and threshold factors applied during the processing pipeline.  ...  active learning.  ...  different thresholds used in each analysis and every graph theory metric is represented by a different symbol.  ... 
doi:10.1101/2020.10.29.359778 fatcat:luqaqcpc25bgzhjtsneqjno3z4

Cartwright, Causality, and Coincidence

Deborah G. Mayo
1986 PSA Proceedings of the Biennial Meeting of the Philosophy of Science Association  
He can rule out the alternative non-statistical theory by affirming the (approximate) truth of the statistical one given in Einstein's theory of Brownian motion.  ...  Statistics allows us to learn about the probabilistic relationship between characteristics of experimental results (i.e., statistics) and parameters of the population from which the results  ...  This suggests, for example, that a model for Brownian motion is provided by viewing a particle as taking a simple random walk: it has the same chance of being displaced a given amount X in either a positive  ... 
doi:10.1086/psaprocbienmeetp.1986.1.193106 fatcat:xpmibxuf3raahn4pc7gbf4b6ea

Action as an innate bias for visual learning

A. L. Yuille, H. H. Bulthoff
2012 Proceedings of the National Academy of Sciences of the United States of America  
Recently, computational mod-elers are starting to use motion sequences; e.g., Si et al. (20) have described a method for learning causality and actions from motion sequences.  ...  As the authors state (8) , most computational theories are based on the statistics of images and neglect concepts like action, which have a causal flavor, although recent work has extended statistics  ... 
doi:10.1073/pnas.1215851109 pmid:23091008 pmcid:PMC3497765 fatcat:kw7oeaz2mjdl7nytij6lzqh4wm

Controlling model complexity in flow estimation

Duric, Li, Wechsler, Cherkassky
2003 Proceedings Ninth IEEE International Conference on Computer Vision  
This paper describes a novel application of Statistical Learning Theory (SLT) to control model complexity in flow estimation.  ...  We demonstrate an application of this method on both synthetic and real image sequences and use it for motion interpolation and extrapolation.  ...  Introduction Statistical Learning Theory (SLT) [13, 5] provides the mathematical framework for estimating motion models from finite training data; it enables a better understanding of problems related  ... 
doi:10.1109/iccv.2003.1238445 dblp:conf/iccv/DuricLWC03 fatcat:7ema2oeranhbhjjokrvjhclgoq

Acquisition of visual priors and induced hallucinations in chronic schizophrenia [article]

Vincent Valton, Povilas Karvelis, Katie L. Richards, Aaron R. Seitz, Stephen M. Lawrie, Peggy Seriès
2018 bioRxiv   pre-print
To further test these theories, we here use a visual statistical learning task known to induce rapid implicit learning of the stimulus statistics (Chalk et al., 2010).  ...  AbstractProminent theories suggest that symptoms of schizophrenia stem from learning deficiencies resulting in distorted internal models of the world.  ...  We used a previously developed statistical learning task (Chalk et al., 2010; Gekas et al., 2013; Karvelis et al., 2018) that is known to induce the rapid acquisition of the statistics of motion stimuli  ... 
doi:10.1101/498568 fatcat:cffchcp7vvfkretboodhvfnqey

What Can We Learn from Biological Vision Studies for Human Motion Segmentation? [chapter]

Cheng Chen, Guoliang Fan
2006 Lecture Notes in Computer Science  
According to this model, object segmentation, motion estimation, and action recognition are results of recurrent feedforward (bottom-up) and feedback (top-down) processes.  ...  We also examine recent research on biological movement perception, such as neural mechanisms and functionalities for biological movement recognition and two major psychological tracking theories.  ...  -How to represent and learn prior knowledge for statistical inference? In general, we assume that prior knowledge is known by certain offline learning algorithm.  ... 
doi:10.1007/11919629_79 fatcat:2uark6vbibdbjosbrz6p3pqpxi

2014 Index IEEE Transactions on Medical Imaging Vol. 33

2014 IEEE Transactions on Medical Imaging  
., +, TMI Jan. 2014 1-10 Tracking Using Motion Estimation With Physically Motivated Inter-Region Constraints.  ...  Rusu, C., +, TMI July 2014 1422-1433 Tracking Using Motion Estimation With Physically Motivated Inter-Region Constraints.  ...  MRI Upsampling Using Feature-Based Nonlocal Means Approach. Jafari-Khouzani, K., 1969 -1985 Numerical Surrogates for Human Observers in Myocardial Motion Evaluation From SPECT Images.  ... 
doi:10.1109/tmi.2014.2386278 fatcat:poarfhfto5bm5mhfl7ugwtw4xy

Video Analysis for Human Behavior Understanding

Jenq-Neng Hwang, Changick Kim, Hsu-Yung Cheng
2010 EURASIP Journal on Advances in Signal Processing  
To overcome these challenges, not only the traditional image processing, computer vision, pattern recognition, and machine learning techniques are required, but also advanced estimation theory and statistical  ...  Finally, statistical background algorithm (SBA) is consistently inferior to the others, so its adoption is not advisable.  ...  To overcome these challenges, not only the traditional image processing, computer vision, pattern recognition, and machine learning techniques are required, but also advanced estimation theory and statistical  ... 
doi:10.1155/2010/402912 fatcat:tlz4nhdoojgizoqcfvzdii3cpu

Aggressive, Tense or Shy? Identifying Personality Traits from Crowd Videos

Aniket Bera, Tanmay Randhavane, Dinesh Manocha
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
Our classification criterion is based on Personality Trait theory. We present a statistical scheme that dynamically learns the behavior of every pedestrian and computes its motion model.  ...  This model is combined with global crowd characteristics to compute the movement patterns and motion dynamics and use them for crowd prediction.  ...  We learn the pedestrian motion model parameters using statistical methods and learn global and local behavior characteristics.  ... 
doi:10.24963/ijcai.2017/17 dblp:conf/ijcai/BeraRM17 fatcat:bzjglvedfbbozn4rbsf336ll34

A Study on Sensor System Latency in VR Motion Sickness

Ripan Kumar Kundu, Akhlaqur Rahman, Shuva Paul
2021 Journal of Sensor and Actuator Networks  
The error between the predicted data and the actual data is compared for statistical methods and deep learning techniques.  ...  The simulation results suggest that the deep learning techniques outperformed the statistical methods in terms of error comparison.  ...  Sensors Most mobile AR and VR devices combine cameras and inertial measurement units (IMUs) for their use for motion estimation.  ... 
doi:10.3390/jsan10030053 fatcat:wda53gkt4fct7d7a3txodmq4ae

A system for learning statistical motion patterns

Weiming Hu, Xuejuan Xiao, Zhouyu Fu, D. Xie, Tieniu Tan, S. Maybank
2006 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Based on the learned statistical motion patterns, we use statistical theory, together with Bayes rule, to detect anomalies and predict behaviors.  ...  In Johnson's work, the number of different behaviors is not estimated and the detection probability theory is not used to identify anomalies and predict motions.  ... 
doi:10.1109/tpami.2006.176 pmid:16929731 fatcat:mg7b35qxtzenrnlmq273fkzd2y

Parameter learning but not structure learning: A Bayesian network model of constraints on early perceptual learning

Melchi M. Michel, Robert A. Jacobs
2007 Journal of Vision  
These ideas are formalized using the notation of Bayesian networks.  ...  We propose a new constraint on early perceptual learning, namely, that people are capable of parameter learningVthey can modify their knowledge of the prior probabilities of scene variables or of the statistical  ...  Using Wallach's theory, we consider constraints on the learning processes underlying cue acquisition.  ... 
doi:10.1167/7.1.4 pmid:17461672 fatcat:rxpbdf3pizgwniapi24f63hlnm

Complexity and specificity of experimentally-induced expectations in motion perception

N. Gekas, M. Chalk, A. R. Seitz, P. Series
2013 Journal of Vision  
Our results can be modeled using a Bayesian framework and discussed in terms of a suboptimality of the statistical learning process under some conditions.  ...  using a bimodal distribution of motion directions such that two directions were more frequently presented than the others.  ...  Acknowledgments We would like to thank Dagmara Panas for her work on an earlier version of the experiment that helped us identify potential issues with the experimental paradigm and how to best address  ... 
doi:10.1167/13.4.8 pmid:23487160 fatcat:pfm4uj7o3jd5vjfu5q42k3epxa

Complexity and specificity of experimentally induced expectations in motion perception

Nikos Gekas, Matthew Chalk, Aaron R Seitz, Peggy Seriès
2013 BMC Neuroscience  
Our results can be modeled using a Bayesian framework and discussed in terms of a sub-optimality of the statistical learning process under some conditions.  ...  using a bimodal distribution of motion directions such that two directions were more frequently presented than the others.  ...  Acknowledgments We would like to thank Dagmara Panas for her work on an earlier version of the experiment that helped us identify potential issues with the experimental paradigm, and how to best address  ... 
doi:10.1186/1471-2202-14-s1-p355 pmcid:PMC3704676 fatcat:z5vqyhx6sjgbfliypgrhaya6m4
« Previous Showing results 1 — 15 out of 117,336 results