Filters








28,169 Hits in 4.1 sec

Explicitly Task Oriented Probabilistic Active Vision for a Mobile Robot [chapter]

Pablo Guerrero, Javier Ruiz-del-Solar, Miguel Romero
2009 Lecture Notes in Computer Science  
In the presented work, an explicitly task oriented probabilistic active vision system is proposed.  ...  As a test-bed for the presented active vision approach, we selected a robot soccer attention problem: goal covering by a goalie player.  ...  Conclusions We have presented a probabilistic and explicitly task oriented active vision system which is able to select in which object the robot should focus.  ... 
doi:10.1007/978-3-642-02921-9_8 fatcat:nmfhfo6dwnezdc7ynrwhgna6hu

Pattern Classification and Analysis of Brain Maps through fMRI data with Multiple Methods

Dr H N Suma Suma, Dr S Murali
2010 International Journal of Computer Applications  
The fMRI data is huge, dimensionally dissimilar for different orientation data and also show a lot of variation in the data acquired for different subjects for similar activities.  ...  The use of individually generated activation maps with SPM allows for better scalability to very large subject pools and it has the potential to integrate data at the activation map level that would be  ...  The visiomemory task involves both bilateral vision task and also the non bilateral memory task.  ... 
doi:10.5120/490-801 fatcat:wmoati23fbccffxgrdru3muzrm

If perception is probabilistic, why does it not seem probabilistic?

Ned Block
2018 Philosophical Transactions of the Royal Society of London. Biological Sciences  
(Visual data are often taken to be activations in early vision.)  ...  If there are many samples, the problem this article started with arises: The samples will be samples of different orientations, so why does not vision reflect all the samples?  ... 
doi:10.1098/rstb.2017.0341 pmid:30061455 fatcat:vmksf3bypjdm7jrh3sivsc32we

Guest editorial: Special issue on active perception

Robert Fitch, Volkan Isler, Pratap Tokekar, Davide Scaramuzza
2018 Autonomous Robots  
Active perception involves controlling sensor parameters to achieve a sensing task.  ...  Sensing modalities include monocular vision, stereo vision,  ...  The special issue was motivated by the workshop "Scaling Up Active Perception," organized by Yiannis Aloimonos, Andrea Censi, Kostas Daniilidis, Volkan Isler, and Stefano Soatto (in alphabetical order)  ... 
doi:10.1007/s10514-018-9695-8 fatcat:x7usikxz7ff7fius5swznswmfi

SPATIAL AND TEMPORAL ELEMENTS OF ANTICIPATION CONSISTENCY OF CHILDREN WITH GENERAL SPEECH RETARDATION

Akhmetzyanova
2014 American Journal of Applied Sciences  
Thus, we face the task to identify the causes of school de-adaptation of children who have speech pathology.  ...  We observed a very low level of development of motor coordination of children with general speech underdevelopment, which level is considered as the reflection of the probabilistic forecast on the level  ...  All tasks of the graphic test targeted detection of the development of fine motor skills of hands and coordination of vision and hand motion.  ... 
doi:10.3844/ajassp.2014.1031.1035 fatcat:rv3iqrbeqjctpmu5kbyskl4kjm

Learning probabilistic discriminative models of grasp affordances under limited supervision

A N Erkan, O Kroemer, R Detry, Y Altun, J Piater, J Peters
2010 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems  
This paper addresses the problem of learning and efficiently representing discriminative probabilistic models of object-specific grasp affordances particularly in situations where the number of labeled  ...  Experimental evaluation shows that combining active and semi-supervised learning is favorable in the existence of to an oracle.  ...  In this paper, we investigate learning probabilistic models of grasp affordances for an autonomous robot equipped with a 3D vision system (see Figure I ).  ... 
doi:10.1109/iros.2010.5650088 dblp:conf/iros/ErkanKDAPP10 fatcat:2gii55sqs5cu7pce22mp7ouewy

Activity Recognition Using Histogram of Oriented Gradient Pattern History

Dipankar Das
2014 International Journal of Computer Science Engineering and Information Technology  
Human activity recognition is an important task in computer vision because it has many application areas such as, healthcare, security, entertainment, and tactical scenarios.  ...  We have experimented with video data of human activity in real environments for three different tasks (browsing, reading, and writing).  ...  INTRODUCTION Recognizing human activity or task from real-time video data is one of the promising and challenging applications of computer vision.  ... 
doi:10.5121/ijcseit.2014.4403 fatcat:7mpeq2amljcfraewpw6lf6ud5m

Volumetric Object Reconstruction in Multi-Camera Scenarios

Enrique Hernández Murillo, Gonzalo López Nicolás, Rosario Aragüés
2019 Jornada de Jóvenes Investigadores del I3A  
On the one hand, active vision could be taken as a viable alternative. This technique may require using a vision-based sensor, mounted on a mobile robot, providing dense 3D input data.  ...  However, one of the main challenges involved in active vision are deformable or mobile objects, which requires an instantaneous perception of the object.  ... 
doi:10.26754/jji-i3a.003572 fatcat:v5jyem6ipjgargnuzaqh6hraga

Collective Activity Detection Using Hinge-loss Markov Random Fields

Ben London, Sameh Khamis, Stephen H. Bach, Bert Huang, Lise Getoor, Larry Davis
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops  
We propose hinge-loss Markov random fields (HL-MRFs), a powerful class of continuous-valued graphical models, for high-level computer vision tasks.  ...  We apply HL-MRFs to the task of activity detection, using principles of collective classification. Our model is simple, intuitive and interpretable.  ...  Conclusion We have shown that HL-MRFs are a powerful class of models for high-level computer vision tasks. When combined with PSL, designing probabilistic models is easy and intuitive.  ... 
doi:10.1109/cvprw.2013.157 dblp:conf/cvpr/LondonKBHGD13 fatcat:ee6bi3pdmndttljkyx2ugrcxhu

The implications of perception as probabilistic inference for correlated neural variability during behavior [article]

Ralf M. Haefner, Pietro Berkes, József Fiser
2015 arXiv   pre-print
Starting from the old idea of perception as probabilistic inference, we show how to use knowledge of the psychophysical task to make easily testable predictions for the impact that feedback signals have  ...  of sensory processing, including the task-dependence of neural response correlations, and the diverging time courses of choice probabilities and psychophysical kernels.  ...  as probabilistic inference even though the brain's internal model for general vision is unknown.  ... 
arXiv:1409.0257v2 fatcat:h2sr4btjozf6thos73ixv6najm

What Do Models of Visual Perception Tell Us about Visual Phenomenology? [chapter]

2022 Neuroscience and Philosophy  
Although a single number could be used to represent a probability computed at a previous stage, here we use "probabilistic" to refer to the representational stage at which the probability is computed.  ...  For example, in an orientation discrimination task, the sensory stage might encode the stimulus orientation as a continuous variable, whereas the decision stage converts that graded sensory response to  ...  Models of Visual Perception and Decision Making Here, we consider four widely used vision models: (1) signal detection theory (SDT), (2) drift diffusion models (DDM), (3) probabilistic population codes  ... 
doi:10.7551/mitpress/12611.003.0014 fatcat:pgbn2w4luzfotcyqzjhdbfc6e4

Adaptive precision pooling of model neuron activities predicts the efficiency of human visual learning

R. A. Jacobs
2009 Journal of Vision  
When performing a perceptual task, precision pooling occurs when an organism's decisions are based on the activities of a small set of highly informative neurons.  ...  We trained human subjects on a visual slant discrimination task and found their performances to be suboptimal relative to an ideal probabilistic observer. Why were subjects suboptimal learners?  ...  In addition, consider the subset of MT neurons whose activities are informative for this task, such as neurons that are reliably more active with 0-stimuli than with 3-stimuli.  ... 
doi:10.1167/9.4.22 pmid:19757931 fatcat:2ibvquwqsjeyhblqprjjdkwhvq

Striatal dopaminergic modulation of reinforcement learning predicts reward—oriented behavior in daily life

Zuzana Kasanova, Jenny Ceccarini, Michael J. Frank, Thérèse van Amelsvoort, Jan Booij, Alexander Heinzel, Felix Mottaghy, Inez Myin-Germeys
2017 Biological Psychology  
We therefore combined, for the first time, a DA D 2/3 receptor [ 18 F]fallypride PET during a probabilistic reinforcement learning (RL) task with a six day ecological momentary assessments (EMA) of reward-related  ...  Furthermore, individual variability in the extent of reward-induced DA release in the right caudate nucleus and ventral striatum modulated the tendency to be actively engaged in a behavior if the active  ...  by the probabilistic reward task, and separately by EMA in the everyday life.  ... 
doi:10.1016/j.biopsycho.2017.04.014 pmid:28461214 fatcat:olt2jlbp2vaopfo7yqqsuxkox4

Extracting data from human manipulation of objects towards improving autonomous robotic grasping

Diego R. Faria, Ricardo Martins, Jorge Lobo, Jorge Dias
2012 Robotics and Autonomous Systems  
This will enable modelling a class of tasks from sets of repeated demonstrations of the same task, so that a generalised probabilistic representation is derived to be used for task planning in artificial  ...  In this work, we study how humans manipulate simple daily objects, and construct a probabilistic representation model for the tasks and objects useful for autonomous grasping and manipulation by robotic  ...  The NotActive, LowActive and HighActive define the level of activation of that region during the in-hand manipulation task.  ... 
doi:10.1016/j.robot.2011.07.020 fatcat:nlnage3pefamnmry4hqwgdl23q

Probabilistic brains: knowns and unknowns

Alexandre Pouget, Jeffrey M Beck, Wei Ji Ma, Peter E Latham
2013 Nature Neuroscience  
To date, however, these theories have only been applied to very simple tasks.  ...  Probabilistic inference for multisensory integration Multisensory integration provides one of the best illustrations of the power of the probabilistic approach.  ...  For instance, the activity of neurons in V1 is typically interpreted as encoding orientation, whereas neurons in area MT are thought to encode direction of motion.  ... 
doi:10.1038/nn.3495 pmid:23955561 pmcid:PMC4487650 fatcat:creg65nvmbhm3pprupmwc2c33a
« Previous Showing results 1 — 15 out of 28,169 results