416,541 Hits in 5.1 sec

A Multiobject Tracking Framework for Interactive Multimedia Applications

M. Yeasin, E. Polat, R. Sharma
2004 IEEE transactions on multimedia  
Such systems include robots operating in a dynamic and uncertain environment, biomedical systems, and advanced human computer interfaces.  ...  Some of the research results are being used for developing commercial products by Advanced Interface Technologies (AIT), Inc., a private company in partnership with Penn State.  ...  PROPOSED FRAMEWORK This paper presents an integrated framework for detecting and tracking body parts (hands and faces) of multiple people for collaborative human computer interaction.  ... 
doi:10.1109/tmm.2004.827514 fatcat:hifsikzj3fbnbey5xshuwpurhe

A Face Tracking Algorithm for User Interaction in Mobile Devices

Abdullah Bulbul, Zeynep Cipiloglu, Tolga Capin
2009 2009 International Conference on CyberWorlds  
A new face tracking algorithm, and a human-computer interaction technique based on this algorithm, are proposed for use on mobile devices.  ...  The solution is based on color comparisons and works on images gathered from the front camera of a device.  ...  ACKNOWLEDGMENT We thank FP7-213349 All 3D Imaging Phone project for the hardware support.  ... 
doi:10.1109/cw.2009.9 dblp:conf/vw/BulbulCC09 fatcat:3ycnngcsvndr7kvjvcyufq77ai

Detecting Interactions from Neural Networks via Topological Analysis

Zirui Liu, Qingquan Song, Kaixiong Zhou, Ting-Hsiang Wang, Ying Shan, Xia Hu
2020 Neural Information Processing Systems  
Detecting statistical interactions between input features is a crucial and challenging task.  ...  Specially, we propose a new measure for quantifying interaction strength, based upon the well-received theory of persistent homology.  ...  The authors thank the Texas A&M College of Engineering and Texas A&M University.  ... 
dblp:conf/nips/LiuSZWSH20 fatcat:dl67eb5ylbcoblna2725lxg5ha

A web-enabled video indexing system

Jian Zhou, Xiao-Ping Zhang
2004 Proceedings of the 6th ACM SIGMM international workshop on Multimedia information retrieval - MIR '04  
For gradual transition detection, new features are introduced for dissolve detection. The proposed dissolve detector is based on a combined analysis of mean-variance-skewness of intensity.  ...  Compared with existing variance-based approaches, the introduced new features improve the discrimination ability on shot boundaries. We also describe methods for eliminating false positives.  ...  By introducing these new features and criteria, the proposed dissolve detector has provided a new way to identify and analyze dissolve transitions.  ... 
doi:10.1145/1026711.1026761 dblp:conf/mir/ZhouZ04 fatcat:bdfnty43ujdafhbw6tza6n3som

Beyond News Contents: The Role of Social Context for Fake News Detection [article]

Kai Shu, Suhang Wang, Huan Liu
2018 arXiv   pre-print
We propose a tri-relationship embedding framework TriFN, which models publisher-news relations and user-news interactions simultaneously for fake news classification.  ...  We conduct experiments on two real-world datasets, which demonstrate that the proposed approach significantly outperforms other baseline methods for fake news detection.  ...  A TRI-RELATIONSHIP EMBEDDING FRAMEWORKIn this section, we present the details of the proposed framework TriFN for modeling tri-relationship for fake news detection.  ... 
arXiv:1712.07709v2 fatcat:sdlieawisbas5dothkyensl4cq

Preventing Feature Interactions by Constraints

Jihong Zuo, Qianxiang Wang, Hong Mei
2006 30th Annual International Computer Software and Applications Conference (COMPSAC'06)  
As software systems evolve by adding new extensions some unexpected conflicts may occur, which is known as the Feature Interaction Problem (FIP).  ...  This paper analyzes the problems and proposes to enforce necessary constraints to prevent the FIP.  ...  Interactions are detected if some "bad" state is reachable. In [10] , the base and features are specified as a set of processes in LOTOS.  ... 
doi:10.1109/compsac.2006.150 dblp:conf/compsac/ZuoWM06 fatcat:nykviooscraevfrfdbw7wq7mta

Investigation on SMT Product Defect Recognition Based on Multi-Source and Multi-Dimensional Data Reconstruction

Jiantao Chang, Zixuan Qiao, Qibin Wang, Xianguang Kong, Yunsong Yuan
2022 Micromachines  
Firstly, the correlation between features and defects was enhanced by feature interaction, selection, and conversion.  ...  Compared with four other methods, the proposed defect recognition model has higher accuracy and provides a new approach to improving the defect recognition rate in the SMT production quality control process  ...  Thus, RF is applied for the selection of new features after feature interaction. The process for calculating the random forest importance score is as follows.  ... 
doi:10.3390/mi13060860 pmid:35744474 pmcid:PMC9228397 fatcat:hylp47flsfh2lgi26miiv4eequ

Indian Sign Language Automated Learning using Region Bound Algorithm

In this paper, a representation of sign language symbol for automated sign language detection and decision making is proposed.  ...  This paper presents a novel technique to Indian sign language detection for automated learning to develop an interface towards elimination of communication gap between vocally disabled and common individual  ...  The approach defined a new system model for Indian sign language detection based on region bound features of a given cue sample.  ... 
doi:10.35940/ijitee.k2210.0981119 fatcat:zfeaoq634ne3pc3qfekryc3o3a

The Feature Interaction Problem in the IN: In search of a global solution [chapter]

Nadir Belarbi, Dominique Gaiti
1997 Intelligent Networks and Intelligence in Networks  
The purpose of our article is to give a general overview of the feature interactions problem considered as one of the main problem in the IN.  ...  Telecommunication operators are looking for new types of services to be introduced in multimedia networks.  ...  Detection methodologies for instance try to propose a resolution step for the detected interaction and that seems natural.  ... 
doi:10.1007/978-0-387-35066-0_6 fatcat:celugxyp3fdy7lplcuw4va2yhm

Designing Threat Detection Model for Emerging Software Platform

2021 International Journal of Advanced Trends in Computer Science and Engineering  
which shares the common devices and proposed a Threat detection model to find out the security risks in emerging software platforms.  ...  The undertaken study reveals the emergent software, their security challenges, features of Internet of Things and Android platforms, to detect the venerable and dangerous interactions between applications  ...  The evolution analyzer detects the app interaction events as well as their inspection, survival and elimination.  ... 
doi:10.30534/ijatcse/2021/1281032021 fatcat:6w64wrf2bjfkxmsbywjmcqgbgy

Detection of Hidden Objectives and Interactive Objective Reduction [article]

Seyed Mahdi Shavarani, Manuel López-Ibáñez, Richard Allmendinger
2022 arXiv   pre-print
The proposed method, which is based on univariate feature selection, is computationally effective and can be integrated into any ranking-based interactive EMOA.  ...  , to detect and eliminate the irrelevant objectives during the optimization process and replace them with hidden ones, if any.  ...  A. Feature Selection We explore two feature selection methods in this study: Uni-variate feature selection and Recursive Feature Elimination (RFE).  ... 
arXiv:2206.01320v1 fatcat:zbjj33zw3nedplfas3sknacn54

Framework for Providing Security in Private Cloud using Machine Learning Techniques

2019 International Journal of Engineering and Advanced Technology  
In this paper, a two level framework is proposed which can be used to detect unknown new attacks using machine learning techniques.  ...  The Model with Support Vector Machine for supervised machine learning, Gradual Feature Reduction (GFR) for feature selection and K-means for unsupervised algorithm provided the optimum efficiency of 94.56  ...  Ragha [5] have proposed a model for classification of attacks using the hybrid feature selection method which combines the wrapper and filter methods.  ... 
doi:10.35940/ijeat.f9121.109119 fatcat:qhe6bsxmfndqrf22ueymi5kuuu

Gesture Recognition using CNN and RNN

2020 International journal of recent technology and engineering  
A real-time Hand Gesture Recognition System is implemented and is used for operating electronic appliances.  ...  Gesture Recognition is a major area in HumanComputer Interaction (HCI). HCI allows computers to capture and interpret human gestures as commands.  ...  Hand Detection For a real-time hand gesture, edges of the hand are detected to extract the features. The hand is detected based on the number of fingers in the gesture and orientation of a gesture.  ... 
doi:10.35940/ijrte.b3417.079220 fatcat:m6qjotzg4rcmla3ca73wdkwsq4

Feature Based Face Detection in HRI

Nibedita Mishra, Department of Industrial Design, NIT Rourkela, Odisha, India, Bunil Kumar Balabantaray, Omprakash Sahu, Bibhuti Bhusan Biswal
2016 Journal of Image and Graphics  
In this work, a method for face detection using LabVIEW is proposed. ELM technique is used to filter real face images along with the corner filter.  ...  Human being is becoming closer and more interested in the collaboration with robots in their daily life. For a better integration with robots, Face detection is a very essential aspect of HRI.  ...  In this work, a feature based human face detection system is proposed for human robot interaction.  ... 
doi:10.18178/joig.4.2.84-88 fatcat:jzcdnvq6lfch3do3wyxh3e7fsi

Real-time image processing for augmented reality on mobile devices

Zhihan Lv, Jaime Lloret, Houbing Song
2021 Journal of Real-Time Image Processing  
Augmented Reality (AR) is a key technology that is going to facilitate a paradigm shift in the way users interact with data and has only just recently been recognized as a viable solution for solving many  ...  Modern smartphones and tablet computers offer multi-core processors and graphics processing units, which have opened up new application possibilities such as augmented reality, virtual reality, and 3D  ...  and Implementation of Library Document Push System" [5] proposes a new data visualization and interactive design process.  ... 
doi:10.1007/s11554-021-01097-9 fatcat:732vv2mx2bdpxediczivjpum34
« Previous Showing results 1 — 15 out of 416,541 results