4,784 Hits in 5.6 sec

Design of Visual Communication Effect Evaluation Method of Artworks Based on Machine Learning

Hang Li, Ran Liu, Lu Wang, Jie Zhang
2022 Mobile Information Systems  
Therefore, computational aesthetics came into being, that is, using a computer model to assist in quantitative evaluation of visual artworks.  ...  With the rapid development of computer and digital media technology, more and more visual artworks are created, preserved, and transmitted digitally, which has become an indispensable spiritual wealth  ...  SVM is generally divided into support vector classification machine and support vector regression machine.  ... 
doi:10.1155/2022/4566185 doaj:0982ec57871e4ea4bf5cb419a4339939 fatcat:4oxs45yysbhsfdcg6lxesjviwu

An Application of Deep Learning to Tactile Data for Object Recognition under Visual Guidance

Ghazal Rouhafzay, Ana-Maria Cretu
2019 Sensors  
Trained classifiers are tested on 4560 new sequential tactile data and the CNN trained over tactile data from object contours selected by the model of visual attention yields an accuracy of 98.97% which  ...  Two different methods for sequential data classification are then implemented using Convolutional Neural Networks (CNN) and conventional classifiers, including support vector machines and k-nearest neighbors  ...  Conflicts of Interest: The authors declare no conflicts of interest.  ... 
doi:10.3390/s19071534 fatcat:zppwlnrv2bck3itiiuqmkc76um

Exploiting Surroundedness for Saliency Detection: A Boolean Map Approach

Jianming Zhang, Stan Sclaroff
2016 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Based on a Gestalt principle of figure-ground segregation, BMS computes saliency maps by analyzing the topological structure of Boolean maps. BMS is simple to implement and efficient to run.  ...  Abstract A novel Boolean Map based Saliency (BMS) model is proposed. An image is characterized by a set of binary images, which are generated by randomly thresholding the image's color channels.  ...  This work was supported in part through grants from the US National Science Foundation #1029430, #0910908, and #0855065.  ... 
doi:10.1109/tpami.2015.2473844 pmid:26336114 fatcat:ra253jx625cuddlr4z7oakhjjm

S_Kernel: A New Symmetry Measure [chapter]

Vito Di Gesù, Bertrand Zavidovique
2005 Lecture Notes in Computer Science  
For the measure we compute a modified difference between respective surfaces of a pattern and its kernel. That founds an efficient algorithm to attention focusing on symmetric patterns.  ...  Symmetry is an important feature in vision. Several detectors or transforms have been proposed. In this paper we concentrate on a measure of symmetry.  ...  of the application of the S-kernel algorithm (SKA) to attention focusing.  ... 
doi:10.1007/11590316_8 fatcat:dwyybqbahjgizmmanmofq5opra

A Multi-modal Attention System for Smart Environments [chapter]

B. Schauerte, T. Plötz, G. A. Fink
2009 Lecture Notes in Computer Science  
Focusing their attention to the most relevant information is a fundamental biological concept, which allows humans to (re-)act rapidly and safely in complex and unfamiliar environments.  ...  This principle has successfully been adopted for technical systems where sensory stimuli need to be processed in an efficient and robust way.  ...  Since reactivity is critical to support the visual perception of all camera-based applications through the overt attention mechanism (Sec. 4.2), we evaluate the run-time of the camera orientation optimization  ... 
doi:10.1007/978-3-642-04667-4_8 fatcat:4xntd3weszfblafzhx5ucdftfy

Saliency Detection: A Boolean Map Approach

Jianming Zhang, Stan Sclaroff
2013 2013 IEEE International Conference on Computer Vision  
Based on a Gestalt principle of figure-ground segregation, BMS computes saliency maps by analyzing the topological structure of Boolean maps. BMS is simple to implement and efficient to run.  ...  A novel Boolean Map based Saliency (BMS) model is proposed. An image is characterized by a set of binary images, which are generated by randomly thresholding the image's color channels.  ...  This work was supported in part through grants from the US National Science Foundation #1029430, #0910908, and #0855065.  ... 
doi:10.1109/iccv.2013.26 dblp:conf/iccv/ZhangS13 fatcat:ibjml6c6ovfjrm6qgypmi63z4y

Improving Sentiment Classification of Restaurant Reviews with Attention-Based Bi-GRU Neural Network

Liangqiang Li, Liang Yang, Yuyang Zeng
2021 Symmetry  
, so we combined Word2vec, Bi-GRU, and Attention method to build a sentiment analysis model for online restaurant reviews.  ...  The significant advantage of Bi-GRU is the guaranteed symmetry of the hidden layer weight update, to take into account the context in online restaurant reviews and to obtain better results with fewer parameters  ...  KNN is a classification algorithm whose basic principle is to compute the K values that are most similar to the centroid.  Support Vector Machine (SVM).  ... 
doi:10.3390/sym13081517 doaj:756b667ce8b54f4f8156e9d195f0cb87 fatcat:y2z65ghrzjes7bgl3w57p3ed2y

A tutorial explaining a machine vision model that emulates human performance when it recovers natural 3D scenes from 2D images

Yunfeng Li, Tadamasa Sawada, Longin Jan Latecki, Robert M. Steinman, Zygmunt Pizlo
2012 Journal of Mathematical Psychology  
This tutorial has two purposes: (i) it provides an example of a computational model that emulates what human beings see in natural environments, and (ii) it explains why, as well as how, each computation  ...  The fact that a 3D symmetry can be detected in a 2D asymmetrical image through an application of a 2D transformation and its invariants simplifies the problem substantially.  ...  The solutions call attention to the importance of non-visual, as well as to visual, a priori constraints.  ... 
doi:10.1016/ fatcat:mkfxvzyfcngx7owb6wbm55dm6q

Commentaries on "Learning Sensorimotor Control with Neuromorphic Sensors: Toward Hyperdimensional Active Perception" [Science Robotics Vol. 4 Issue 30 (2019) 1-10 [article]

Denis Kleyko and Ross W. Gayler and Evgeny Osipov
2020 arXiv   pre-print
Our experience is that hyperdimensional computing is very different from other approaches to computation and that it can take considerable exposure to its concepts before attaining practically useful understanding  ...  Therefore, in order to provide an overview of the area to the first time reader of [1], the commentary includes a brief historic overview as well as connects the findings of the article to a larger body  ...  In the light of the present very high level of attention to the area of autonomous AI-empowered systems from the industry and the society, we hope and believe that the application of VSAs in robotics will  ... 
arXiv:2003.11458v1 fatcat:iwhvamkkffeylb6hjrztdxssp4

Learning to Model Task-Oriented Attention

Xiaochun Zou, Xinbo Zhao, Jian Wang, Yongjia Yang
2016 Computational Intelligence and Neuroscience  
For many applications in graphics, design, and human computer interaction, it is essential to understand where humans look in a scene with a particular task.  ...  Experimental results demonstrate the importance of the target information in the prediction of task-oriented visual attention.  ...  Acknowledgments The work is supported by NSF of China (nos. 61117115 and 61201319), the Fundamental Research Funds for the Central Universities, and NWPU "Soaring Star" and "New Talent and Direction" Program  ... 
doi:10.1155/2016/2381451 pmid:27247561 pmcid:PMC4876208 fatcat:d7s33wkmcvgwxfevul57c4poa4

Review of computational neuroaesthetics: bridging the gap between neuroaesthetics and computer science

Rui Li, Junsong Zhang
2020 Brain Informatics  
Then machine learning algorithms and computational models in computational aesthetics are enumerated.  ...  The topic of aesthetics, in combination with other disciplines such as neuroscience and computer science, has brought out the burgeoning fields of neuroaesthetics and computational aesthetics within less  ...  Acknowledgements Not applicable.  ... 
doi:10.1186/s40708-020-00118-w pmid:33196915 fatcat:qwtdlov6bba23i72covsoxm46a

Research on Social Robot's Whole Body Low-Cost Tactile Perception System Based on Event-trigger for Natural Interaction Scenarios

Shengzhao Lin, Jionglong Su, Sifan Song, Jiaming Zhang
2021 IEEE Access  
electronics, examination, then applied to the social robot's whole body; 2) Establishment of the tactile interactive model and an event-triggered perception model in a social interactive application for  ...  In particular, the cosine k-nearest neighbors and quadratic support vector machine achieve an overall mean accuracy rate of more than 68%, with an individual accuracy rate of more than 80%.  ...  Gastaldo et al. used support vector machine (SVM) to process tactile mode information [49, 50] .  ... 
doi:10.1109/access.2021.3053117 fatcat:h7ojwwgbond4pd7towvvl6s3fi

Issues in Robot Vision

Goesta H. Granlund
1993 Procedings of the British Machine Vision Conference 1993  
We will deal with aspects of pre-attentive versus attentive vision, control mechanisms for low level focus of attention, representation of motion as the orientation of hyperplanes in multdimensional time-space  ...  Issues of scale will be touched upon.  ...  Such an indiscriminate application of computation power is very costly, and as complexity in the desired processing is increasing, it becomes necessary to find methods to restrict the attention to regions  ... 
doi:10.5244/c.7.1 dblp:conf/bmvc/Granlund93 fatcat:v54m46i2zfhbxnqbzuetz2lysa

Multilingual Conversational Systems to Drive the Collection of Patient-Reported Outcomes and Integration into Clinical Workflows

Izidor Mlakar, Valentino Šafran, Daniel Hari, Matej Rojc, Gazihan Alankuş, Rafael Pérez Luna, Umut Ariöz
2021 Symmetry  
create an omni-comprehensive system enabling symmetric computer-mediated interaction.  ...  In this paper, we introduce the main components of the system, including the mHealth application, the Open Health Connect platform, and algorithms to deliver speech enabled 3D embodied conversational agent  ...  The embedding vectors are directed into a series of Microservices to Support Fully Symmetric Interaction Model 4.1.  ... 
doi:10.3390/sym13071187 doaj:ad26faa1719c4fce8925c2bd74fabf77 fatcat:levb6l3xirgchk57vzcl364jti

A Multitask Convolutional Neural Network for Artwork Appreciation

Tian Tian, Feng Nan, Chia-Huei Wu
2022 Mobile Information Systems  
using machines, which has important applications and scientific significance in the automated analysis of large-scale paintings and the computational modeling of perception by machines.  ...  The computational aesthetics of pictorial art is an important part of human artistic creation, and the computational aesthetics of pictorial art images is a computationally computable human aesthetic process  ...  Acknowledgments This work is supported by the Dalian Polytechnic University.  ... 
doi:10.1155/2022/8804711 fatcat:kiz56kb5tncafaywrg2tkl3d4u
« Previous Showing results 1 — 15 out of 4,784 results