3,132 Hits in 7.1 sec

Action-Affect Classification and Morphing using Multi-Task Representation Learning [article]

Timothy J. Shields, Mohamed R. Amer, Max Ehrlich, Amir Tamrakar
2016 arXiv   pre-print
We depart from traditional approaches for time-series data analytics by proposing a multi-task learning model that learns a shared representation that is well-suited for action-affect classification as  ...  We propose a new model that enhances the CRBM model with a factored multi-task component to become Multi-Task Conditional Restricted Boltzmann Machines (MTCRBMs).  ...  Acknowledgments This research was partially developed with funding from the Defense Advanced Research Projects Agency (DARPA) and the Air Force Research Laborotory  ... 
arXiv:1603.06554v1 fatcat:qkupuqbbina5vib4w5bl45z6du

An Efficient Privacy-preserving Deep Learning Scheme for Medical Image Analysis

J. Andrew Onesimu, J Karthikeyan
2020 Journal of Information Technology Management  
An augmented convolutional layer and image morphing are two main components of MpLe scheme. Data providers morph the images without privacy information using image morphing component.  ...  The human unrecognizable image is then delivered to the service providers who then apply deep learning algorithms on morphed data using augmented convolution layer without any performance penalty.  ...  CIFAR dataset is image dataset used for classification tasks. There are two variants based on the number of classes they are CIFAR-10 and CIFAR-100.  ... 
doi:10.22059/jitm.2020.79191 doaj:9a2565b20f8740b98d10c745c9cae1c9 fatcat:fqbifqdmeze7vgn35wj3clngde

Multi-Scale Group Transformer for Long Sequence Modeling in Speech Separation

Yucheng Zhao, Chong Luo, Zheng-Jun Zha, Wenjun Zeng
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
The key ideas are group self-attention, which significantly reduces the complexity, and multi-scale fusion, which retains Transform's ability to capture long-term dependency.  ...  To tackle this issue, we propose a novel variation of Transformer, named multi-scale group Transformer (MSGT).  ...  We propose multi-dueling Q-learning named as MQ-learning that takes as input the state representation and gives as output the value of a set of actions based on dueling Q-learning .  ... 
doi:10.24963/ijcai.2020/446 dblp:conf/ijcai/GaoZG20 fatcat:kal2j4wg4rbafpc7rqsdw6dfym

Is it the real deal? Perception of virtual characters versus humans: an affective cognitive neuroscience perspective

Aline W. de Borst, Beatrice de Gelder
2015 Frontiers in Psychology  
Subsequently, we consider if and when one perceives differences in action representation by artificial agents versus humans.  ...  and affective neuroimaging studies.  ...  Pia Tikka, Klaus Förger, and Meeri Mäkäräinen for fruitful discussions on this topic. AdB and BdG were supported by FP7/2007-2013, ERC grant agreement number 295673.  ... 
doi:10.3389/fpsyg.2015.00576 pmid:26029133 pmcid:PMC4428060 fatcat:7esovhhxwrba5pkm2fim32k7iq

Multi-set Canonical Correlation Analysis for 3D Abnormal Gait Behaviour Recognition based on Virtual Sample Generation

Jian Luo, Tardi Tjahjadi
2020 IEEE Access  
These are projected onto a uniform pattern space using deep learning based multi-set canonical correlation analysis.  ...  The features of point cloud data are then converted to a high-level structured representation of the body. The parametric body model is used for VSG based on the estimated body pose and shape data.  ...  To learn the data tendency in SSS tasks is important for VSG.  ... 
doi:10.1109/access.2020.2973898 fatcat:oxark47ikrhg7k3dg7zyedar6y

Face Verification Across Age Progression using Enhanced Convolution Neural Network

Areeg Mohammed Osman, Serestina Viriri
2020 Signal & Image Processing An International Journal  
for feature extraction and classification.  ...  This paper proposes a deep learning method for facial verification of aging subjects. Facial aging is a texture and shape variations that affect the human face as time progresses.  ...  The Multi-class SVM technique is to use a one-versus-all classification approach to represent the output of the k-th SVM as in (7) .  ... 
doi:10.5121/sipij.2020.11504 fatcat:wstnbndwivchfmklu65nsubqiu

NLPGym – A toolkit for evaluating RL agents on Natural Language Processing Tasks [article]

Rajkumar Ramamurthy, Rafet Sifa, Christian Bauckhage
2020 arXiv   pre-print
Reinforcement learning (RL) has recently shown impressive performance in complex game AI and robotics tasks.  ...  With the work reported here, we therefore release NLPGym, an open-source Python toolkit that provides interactive textual environments for standard NLP tasks such as sequence tagging, multi-label classification  ...  Multi-label Classification (MLC) Multi-label classification is a generalization of several NLP tasks such as multi-class sentence classification and label ranking [33] .  ... 
arXiv:2011.08272v1 fatcat:6cltezznkzbwxl6x7hgq2kztoq

Toddler-Guidance Learning: Impacts of Critical Period on Multimodal AI Agents [article]

Junseok Park, Kwanyoung Park, Hyunseok Oh, Ganghun Lee, Minsu Lee, Youngki Lee, Byoung-Tak Zhang
2022 arXiv   pre-print
We formalize the critical period and Toddler-guidance learning in the reinforcement learning (RL) framework.  ...  We evaluate the impact of critical periods on AI agents from two perspectives: how and when they are guided best in both uni- and multimodal learning.  ...  -10970/16%) grant funded by the Korean government, and the CARAI (UD190031RD/16%) grant funded by the DAPA and ADD.  ... 
arXiv:2201.04990v1 fatcat:lyvailttjjecle5eyso24rayoe

Multi-voxel pattern analysis in human hippocampal subfields

Heidi M. Bonnici, Martin J. Chadwick, Dharshan Kumaran, Demis Hassabis, Nikolaus Weiskopf, Eleanor A. Maguire
2012 Frontiers in Human Neuroscience  
A complete understanding of the hippocampus depends on elucidating the representations and computations that exist in its anatomically distinct subfields.  ...  In parallel, such scanning has facilitated the use of multi-voxel pattern analysis (MVPA) to examine information present in the distributed pattern of activity across voxels.  ...  We thank Peter Aston and the Imaging Support team for technical assistance.  ... 
doi:10.3389/fnhum.2012.00290 pmid:23087638 pmcid:PMC3474998 fatcat:66mdaf67uncy3aimczi567md5u

Interactions in Augmented and Mixed Reality: An Overview

Theofilos Papadopoulos, Konstantinos Evangelidis, Theodore H. Kaskalis, Georgios Evangelidis, Stella Sylaiou
2021 Applied Sciences  
However, although they serve their purpose, various naming trends overlap in terminology, diverge in definitions, and lack modality and conceptual framework classifications.  ...  The latest technological advancements in sensors, processing power and technologies, including the internet of things and the 5G GSM network, led to innovative and advanced input methods and enforced computer  ...  A complete representation of our proposed classification using a modality-based interactionoriented diagram that visualizes all the identified modalities, contexts, and methods.  ... 
doi:10.3390/app11188752 fatcat:znford2gffco7mx23oxvr6jjru

A Survey of Deep Learning Solutions for Multimedia Visual Content Analysis

Muhammad Shahroz Nadeem, Virginia N. L. Franqueira, Xiaojun Zhai, Fatih Kurugollu
2019 IEEE Access  
The increasing use of social media networks on handheld devices, especially smartphones with powerful built-in cameras, and the widespread availability of fast and high bandwidth broadband connections,  ...  It surveys the recent, authoritative, and the best performing DL solutions and lists the datasets used in the development of these deep methods for the identified types of visual analysis problems.  ...  Network variants included a very deep multi-task and hybrid multi-task and hybrid multi-task learning architectures.  ... 
doi:10.1109/access.2019.2924733 fatcat:o6ww2j2effdotdtggf44yjsvea

Classifying design-level requirements using Machine Learning for a Recommender of Interaction Design Patterns

Viridiana Silva, Sandra Edith Nava-Munoz, Luis Castro, Francisco E Martinez-Perez, Hector Perez-Gonzalez, Francisco Torres-Reyes
2020 IET Software  
Due to the design task tends to be subjective and prone to errors.  ...  This work aims at presenting and evaluating an interaction design patterns recommendation model based on design-level requirements classification, through the application of supervised machine learning  ...  Acknowledgments The authors thank the National Council for Science and Technology (CONACYT) in Mexico for their support with grant no. 246970.  ... 
doi:10.1049/iet-sen.2019.0291 fatcat:4ercqqfpfjczhkt62voslp7wkm

Self-agency built with sensorimotor processing: Decoding self-other action attribution in the human brain [article]

Ryu Ohata, Tomohisa Asai, Hiroshi Kadota, Hiroaki Shigemasu, Kenji Ogawa, Hiroshi Imamizu
2018 bioRxiv   pre-print
In this study, we have clarified the neural representations corresponding to three processes namely, sensorimotor error, feeling of agency, and judgment of agency.  ...  Finally, the right inferior frontal gyrus shows a distinct representation between self- and other-attribution immediately before reporting the judgment on the movement attribution.  ...  Figure 2 . 2 Motion morphing task 116 (A) Trial timeline.  ... 
doi:10.1101/483420 fatcat:mew4mahd7vh5bksatk3vx23gmi

How active perception and attractor dynamics shape perceptual categorization: A computational model

Nicola Catenacci Volpi, Jean Charles Quinton, Giovanni Pezzulo
2014 Neural Networks  
We test the model in three simulated perceptual categorization tasks, and we discuss its relevance for grounded and sensorimotor theories of cognition.  ...  We present a computational model incorporating these elements and describing action prediction, active perception, and attractor dynamics as key elements of perceptual categorizations.  ...  The research leading to these results has received funding from the European Community's Seventh Framework Programme (FP7/2007(FP7/ -2013 under grant agreements 270108 (Goal-Leaders, supporting GP), and  ... 
doi:10.1016/j.neunet.2014.06.008 pmid:25105744 fatcat:rbh5i3fjvvbr3crejz7ps7rlti

Guest Editorial: The Computational Face

Sergio Escalera, Xavier Baro, Isabelle Guyon, Hugo Jair Escalante, Georgios Tzimiropoulos, Michel Valstar, Maja Pantic, Jeffrey Cohn, Takeo Kanade
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
ACKNOWLEDGMENTS This project has been partially supported by the Spanish projects TIN2015-66951-C2-2-R and TIN2016-74946-P (MINECO/FEDER, UE) and CERCA Programme/Generalitat de Catalunya and by INAOE,  ...  We thank ChaLearn Looking at People sponsors for their support, including Microsoft Research, Google, NVIDIA Coorporation, Amazon, Facebook, and Disney Research.  ...  Deep learning is consolidated as the representation learning methodology of choice in recognition tasks, in particular.  ... 
doi:10.1109/tpami.2018.2869610 fatcat:izmdxwpzujdv3ctx63lrselk24
« Previous Showing results 1 — 15 out of 3,132 results