Filters








67,250 Hits in 7.3 sec

Central and peripheral vision for scene recognition: A neurocomputational modeling exploration

Panqu Wang, Garrison W. Cottrell
2017 Journal of Vision  
However, central vision is more efficient for scene recognition than peripheral, based on the amount of visual area needed for accurate recognition.  ...  Finally, we visualize the features for the two pathways, and find that different preferences for scene categories emerge for the two pathways during the training process.  ...  GWC was supported in part by NSF grant IIS-1219252 and NSF cooperative agreement SMA 1041755 to the Temporal Dynamics of Learning Center, an NSF Science of Learning Center.  ... 
doi:10.1167/17.4.9 pmid:28437797 fatcat:2zskhdq3z5a7bdircxucvh6zma

Deep learning with non-medical training used for chest pathology identification

Yaniv Bar, Idit Diamant, Lior Wolf, Hayit Greenspan, Lubomir M. Hadjiiski, Georgia D. Tourassi
2015 Medical Imaging 2015: Computer-Aided Diagnosis  
This is a first-of-its-kind experiment that shows that deep learning with large scale non-medical image databases may be sufficient for general medical image recognition tasks.  ...  In this work, we examine the strength of deep learning approaches for pathology detection in chest radiograph data.  ...  This encoding schema yields a binary image descriptor with high performance rates on object category recognition. As a benchmark for our approach we have tested several common descriptors.  ... 
doi:10.1117/12.2083124 dblp:conf/micad/BarDWG15 fatcat:egiteq5jqjcgxipbwjcfp6mf3q

An Evoked Potential-Guided Deep Learning Brain Representation For Visual Classification [article]

Xianglin Zheng, Zehong Cao, Quan Bai
2020 arXiv   pre-print
Then, we trained an LSTM network to learn the feature representation space of visual objects for classification.  ...  Our findings suggested that decoding visual evoked potentials from EEG signals is an effective strategy to learn discriminative brain representations for visual classification.  ...  shown the feasibility to decode human visual activities and deep learning for visual classification.  ... 
arXiv:2006.15357v1 fatcat:3mzr3mf5zbbsfkpaadubip4tfi

Deep neural networks: a new framework for modelling biological vision and brain information processing [article]

Nikolaus Kriegeskorte
2015 bioRxiv   pre-print
Human-level visual recognition abilities are coming within reach of artificial systems.  ...  However, the current models are designed with engineering goals and not to model brain computations.  ...  and object categories.  ... 
doi:10.1101/029876 fatcat:lxuwpdhzrvhpdmtyzg33ogwncy

3D ShapeNets: A Deep Representation for Volumetric Shapes [article]

Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, Jianxiong Xiao
2015 arXiv   pre-print
It naturally supports joint object recognition and shape completion from 2.5D depth maps, and it enables active object recognition through view planning.  ...  Our model, 3D ShapeNets, learns the distribution of complex 3D shapes across different object categories and arbitrary poses from raw CAD data, and discovers hierarchical compositional part representations  ...  Efros, Andrew Owens, Antonio Torralba, Siddhartha Chaudhuri, and Szymon Rusinkiewicz for valuable discussion.  ... 
arXiv:1406.5670v3 fatcat:yyoyxqbyqjdxlifvb73x2rnrvu

Deep-BCN: Deep Networks Meet Biased Competition to Create a Brain-Inspired Model of Attention Control

Hossein Adeli, Gregory Zelinsky
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
We compared Deep-BCN's eye movements to those made from 15 people performing a categorical search for one of 25 target object categories, and found that it predicted both the number of fixations during  ...  The mechanism of attention control is best described by biased-competition theory (BCT), which suggests that a top-down goal state biases a competition among object representations for the selective routing  ...  However, NTVA inputs probability distributions associated with features of object categories and does not extract these features from pixels or learn categories from image exemplars.  ... 
doi:10.1109/cvprw.2018.00259 dblp:conf/cvpr/AdeliZ18 fatcat:v7r6m6cqdjeabc6pqeue3myrle

3D ShapeNets: A deep representation for volumetric shapes

Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, Jianxiong Xiao
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
It naturally supports joint object recognition and shape completion from 2.5D depth maps, and it enables active object recognition through view planning.  ...  Our model, 3D ShapeNets, learns the distribution of complex 3D shapes across different object categories and arbitrary poses from raw CAD data, and discovers hierarchical compositional part representation  ...  Efros, Andrew Owens, Antonio Torralba, Siddhartha Chaudhuri, and Szymon Rusinkiewicz for valuable discussion.  ... 
doi:10.1109/cvpr.2015.7298801 dblp:conf/cvpr/WuSKYZTX15 fatcat:tkadr5auafdpvglgmsooo3ysde

Modeling the Contribution of Central Versus Peripheral Vision in Scene, Object, and Face Recognition [article]

Panqu Wang, Garrison Cottrell
2016 arXiv   pre-print
Our results suggest that the relative order of importance of using central visual field information is face recognition>object recognition>scene recognition, and vice-versa for peripheral information.  ...  Having fit the data for scenes, we used the model to predict future data for large-scale scene recognition as well as for objects and faces.  ...  More recent studies even suggest that the central-biased pathway for recognizing faces and peripheral-biased pathway for recognizing scenes are segregated by mid-fusiform sulcus (MFS) to enable fast parallel  ... 
arXiv:1604.07457v1 fatcat:dbgn676bpbglvileqkbgpfnidy

STDP-based spiking deep convolutional neural networks for object recognition

Saeed Reza Kheradpisheh, Mohammad Ganjtabesh, Simon J. Thorpe, Timothée Masquelier
2018 Neural Networks  
Another line of research has demonstrated - using rate-based neural networks trained with back-propagation - that having many layers increases the recognition robustness, an approach known as deep learning  ...  Coding was very sparse, with only a few thousands spikes per image, and in some cases the object category could be reasonably well inferred from the activity of a single higher-order neuron.  ...  Keywords: Spiking Neural Network, STDP, Deep Learning, Object Recognition, and Temporal Coding Primate's visual system solves the object recognition task through hierarchical processing along the ventral  ... 
doi:10.1016/j.neunet.2017.12.005 pmid:29328958 fatcat:jpqv2oqxg5b6hob6l6kufqxqjy

Hierarchical Sparse Coding of Objects in Deep Convolutional Neural Networks

Xingyu Liu, Zonglei Zhen, Jia Liu
2020 Frontiers in Computational Neuroscience  
underling object recognition.  ...  Recently, deep convolutional neural networks (DCNNs) have attained human-level performances on challenging object recognition tasks owing to their complex internal representation.  ...  For each unit (or channel), the activation map was averaged to produce a unit-wise (or channel-wise) activation for each exemplar, and the activation of the unit to an object category was then derived  ... 
doi:10.3389/fncom.2020.578158 pmid:33362499 pmcid:PMC7755594 fatcat:fpqc3xkhwzcjnmsjwirutae2zm

A Deep Structured Model with Radius–Margin Bound for 3D Human Activity Recognition

Liang Lin, Keze Wang, Wangmeng Zuo, Meng Wang, Jiebo Luo, Lei Zhang
2015 International Journal of Computer Vision  
Our model advances the traditional deep learning approaches in two aspects.  ...  Understanding human activity is very challenging even with the recently developed 3D/depth sensors.  ...  In our approach, we suggest an alternative solution for 3D human activity recognition.  ... 
doi:10.1007/s11263-015-0876-z fatcat:gcmxdmteubdbvcj3ah24mt2bp4

Deep Learning for Big Data Analytics [chapter]

Rajendra Akerkar Priti Srinivas Sajja
2019 Zenodo  
The chapter discusses the difficulties while analyzing big data and introduces deep learning as a solution. This chapter discusses various deep learning techniques and models for big data analytics.  ...  Different deep models such as autoencoders, deep belief nets, convolutional neural networks, recurrent neural networks, reinforcement learning neural networks, multi model approach, parallelization, and  ...  Deep learning is suggested for such applications. With deep learning, it is possible to recognize, classify and categorize patterns in data for a machine with comparatively less efforts.  ... 
doi:10.5281/zenodo.5106011 fatcat:vbxkbmzysvh45cwkbii5bck7wu

VoxRec: Hybrid Convolutional Neural Network for Active 3D Object Recognition

Ahmad Karambakhsh, Bin Sheng, Ping Li, Po Yang, Younhyun Jung, David Dagan Feng
2020 IEEE Access  
In this paper, an innovative approach has been suggested for recognizing 3D models.  ...  Deep Neural Network methods have been used to a variety of challenges in automatic 3D recognition.  ...  Our main contributions include: • A new machine learning approach for recognition of a large 3D objects dataset is proposed.  ... 
doi:10.1109/access.2020.2987177 fatcat:qezmg6hxjbh3vhlyx64d2fdu2u

Collaboration Analysis Using Deep Learning [article]

Zhang Guo, Kevin Yu, Rebecca Pearlman, Nassir Navab, Roghayeh Barmaki
2019 arXiv   pre-print
In this paper, we provided a new solution to improve automated collaborative learning analyses using deep neural networks.  ...  Instead of using self-reported questionnaires, which are subject to bias and noise, we automatically extract group-working information by object recognition results using Mask R-CNN method.  ...  The modern history of object recognition goes along with the development of deep learning techniques.  ... 
arXiv:1904.08066v1 fatcat:gabavhnlf5dtzju24ynkvcmlia

OrthographicNet: A Deep Transfer Learning Approach for 3D Object Recognition in Open-Ended Domains [article]

Hamidreza Kasaei
2020 arXiv   pre-print
For this type of robot, open-ended object category learning and recognition is necessary since no matter how extensive the training data used for batch learning, the robot might be faced with a new object  ...  In this work, we present OrthographicNet, a Convolutional Neural Network (CNN)-based model, for 3D object recognition in open-ended domains.  ...  Deep transfer learning can relax these limitations and motivates us to combine deeplearned features with an online classifier to handle the problem of open-ended object category learning and recognition  ... 
arXiv:1902.03057v3 fatcat:vmq5alktivfqdm46wtijqvrzvm
« Previous Showing results 1 — 15 out of 67,250 results