An experimental study on visual tracking based on deep learning

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Krishna Mohan A ◽  
Reddy PVN ◽  
Satya Prasad K
Keyword(s):  
Deep Learning ◽  
Visual Tracking ◽  
Design Methodology ◽  
Oculomotor System ◽  
Great Success ◽  
Main Theme ◽  
Content Type ◽  
Research Status ◽  
Working Together ◽  
Practical Implications

PurposeIn the community of visual tracking or object tracking, discriminatively learned correlation filter (DCF) has gained more importance. When it comes to speed, DCF gives the best performance. The main objective of this study is to anticipate the object visually. For tracking the object visually, the authors proposed a new model based on the convolutional regression technique. Features like HOG & Harris are used for the process of feature extraction. The proposed method will give the best results when compared to other existing methods.Design/methodology/approachThis paper introduces the concept and research status of tracks; later the authors focus on the representative applications of deep learning in visual tracking.FindingsBetter tracking algorithms are not mentioned in the existing method.Research limitations/implicationsVisual tracking is the ability to control eye movements using the oculomotor system (vision and eye muscles working together). Visual tracking plays an important role when it comes to identifying an object and matching it with the database images. In visual tracking, deep learning has achieved great success.Practical implicationsThe authors implement the multiple tracking methods, for better tracking purpose.Originality/valueThe main theme of this paper is to review the state-of-the-art tracking methods depending on deep learning. First, we introduce the visual tracking that is carried out manually, and secondly, we studied different existing methods of visual tracking based on deep learning. For every paper, we explained the analysis and drawbacks of that tracking method. This paper introduces the concept and research status of tracks, later we focus on the representative applications of deep learning in visual tracking.

Machine reengineering: robots and people working smarter together

2017 ◽  
Vol 45 (6) ◽  
pp. 50-54 ◽  
Author(s):  
Prashant Shukla ◽  
H. James Wilson ◽  
Allan Alter ◽  
David Lavieri
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Design Methodology ◽  
It Professionals ◽  
Content Type ◽  
Public Agency ◽  
Intelligent Machines ◽  
Intelligent Machine ◽  
Working Together ◽  
Practical Implications

Purpose The authors explore the potential of machine learning, computers employ that an algorithm to sort data, make decisions and then continuously assess and improve their functionality. They suggest that it be used to power a radical redesign of company processes that they call machine reengineering. Design/methodology/approach The authors interpret a survey of more than a thousand corporate public agency IT professionals on their use of artificial intelligence and machine learning. Findings Companies that embrace machine learning find that it adds value to the work product of their employees and provides companies with new capabilities. Practical implications Working together with an intelligent machine, workers become custodians of powerfully smart tools, tools that personalize work to maximize their most productive ways of working. Originality/value A guide to establishing a culture that empowers employees to thrive alongside intelligent machines.

How Specsavers attracts and nurtures outstanding talent

2012 ◽  
Vol 11 (4) ◽  
pp. 193-198 ◽  
Author(s):  
Leah Newby ◽  
Chris Howarth
Keyword(s):  
Design Methodology ◽  
Joint Venture ◽  
Development Program ◽  
Content Type ◽  
Training Materials ◽  
Recruitment Challenges ◽  
New Strategy ◽  
Working Together ◽  
Hr Strategy ◽  
Practical Implications

PurposeThe aim of this paper is to detail the innovative campaign co‐developed by Words&Pictures and Specsavers to raise the caliber of Specsavers' profile in the optics profession among university optometry graduates, to produce a continuous flow of talent within the company, and to give customers the best service.Design/methodology/approachAdopting a collaborative approach, Specsavers' canvassed the opinions of its employees and joint venture partners to develop a new HR strategy to attract and nurture outstanding talent. In order to implement the new strategy, Specsavers turned to Words&Pictures, which created a high‐end internal brand, INsight, to showcase the new five‐part recruitment and development program.Practical implicationsOrganizations that face similar recruitment challenges would do well to re‐assess the needs of the business, including the inter‐personal and communication skills required by their employees.Originality/valueWorking together, Specsavers and Words&Pictures combined their unique strengths to create a visually stunning, professional, practical, aspirational and fun suite of training materials for pre‐registration optometrists. This has helped to elevate Specsavers' pre‐registration optometrists' program above its competitors and positioned the company as unrivalled in its attitude towards employee acquisition, development and retention.

scholarly journals Developing a new deep learning CNN model to detect and classify highway cracks

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Faris Elghaish ◽  
Saeed Talebi ◽  
Essam Abdellatef ◽  
Sandra T. Matarneh ◽  
M. Reza Hosseini ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Optimization Algorithm ◽  
Design Methodology ◽  
Content Type ◽  
Learning Rates ◽  
Traditional Approaches ◽  
Short Time ◽  
Practical Implications

Purpose This paper aims to Test the capabilities/accuracies of four deep learning pre trained convolutional neural network (CNN) models to detect and classify types of highway cracks, as well as developing a new CNN model to maximize the accuracy at different learning rates. Design/methodology/approach A sample of 4,663 images of highway cracks were collected and classified into three categories of cracks, namely, “vertical cracks,” “horizontal and vertical cracks” and “diagonal cracks,” subsequently, using “Matlab” to classify the sample to training (70%) and testing (30%) to apply the four deep learning CNN models and compute their accuracies. After that, developing a new deep learning CNN model to maximize the accuracy of detecting and classifying highway cracks and testing the accuracy using three optimization algorithms at different learning rates. Findings The accuracies result of the four deep learning pre-trained models are above the averages between top-1 and top-5 and the accuracy of classifying and detecting the samples exceeded the top-5 accuracy for the pre-trained AlexNet model around 3% and by 0.2% for the GoogleNet model. The accurate model here is the GoogleNet model as the accuracy is 89.08% and it is higher than AlexNet by 1.26%. While the computed accuracy for the new created deep learning CNN model exceeded all pre-trained models by achieving 97.62% at a learning rate of 0.001 using Adam’s optimization algorithm. Practical implications The created deep learning CNN model will enable users (e.g. highway agencies) to scan a long highway and detect types of cracks accurately in a very short time compared to traditional approaches. Originality/value A new deep learning CNN-based highway cracks detection was developed based on testing four pre-trained CNN models and analyze the capabilities of each model to maximize the accuracy of the proposed CNN.

Consumer value creation through WhatsApp use

2019 ◽  
Vol 32 (4) ◽  
pp. 455-471
Author(s):  
Jorge Cruz-Cárdenas ◽  
Jorge Guadalupe-Lanas ◽  
Ekaterina Zabelina ◽  
Andrés Palacio-Fierro ◽  
Margarita Velín-Fárez ◽  
...  
Keyword(s):  
Latin American ◽  
Value Creation ◽  
Emotional Support ◽  
Design Methodology ◽  
Instant Messaging ◽  
Role Performance ◽  
Content Type ◽  
Consumer Value ◽  
Depth Interviews ◽  
Practical Implications

Purpose The purpose of this paper is to understand in-depth how consumers create value in their lives using WhatsApp, the leading mobile instant messaging (MIM) application. Design/methodology/approach The study adopts the perspective of customer-dominant logic (CDL) and uses a qualitative multimethod design involving 3 focus groups and 25 subsequent in-depth interviews. The research setting was Ecuador, a Latin American country. Findings Analysis and interpretation of the participants’ stories made it possible to identify and understand the creation of four types of value: maintaining and strengthening relationships; improving role performance; emotional support; and entertainment and fun. In addition, the present study proposes a conceptual model of consumer value creation as it applies to MIM. Practical implications Understanding the way consumers create value in their lives using MIM is important not only for organizations that offer MIM applications, but also for those companies that develop other applications for mobile phones or for those who wish to use MIM as an electronic word-of-mouth vehicle. Originality/value The current study is one of the first to address the topic of consumer behavior in the use of technologies from the perspective of CDL; this perspective enables an integrated qualitative vision of value creation in which the consumer is the protagonist.

scholarly journals Advantages and potential challenges of data management in e-maintenance

2019 ◽  
Vol 25 (3) ◽  
pp. 378-396 ◽  
Author(s):  
Arian Razmi-Farooji ◽  
Hanna Kropsu-Vehkaperä ◽  
Janne Härkönen ◽  
Harri Haapasalo
Keyword(s):  
Data Management ◽  
Design Methodology ◽  
Management Practices ◽  
Future Research ◽  
Conceptual Approach ◽  
Content Type ◽  
Different Types ◽  
Maintenance Systems ◽  
Industry Leader ◽  
Practical Implications

Purpose The purpose of this paper is twofold: first, to understand data management challenges in e-maintenance systems from a holistically viewpoint through summarizing the earlier scattered research in the field, and second, to present a conceptual approach for addressing these challenges in practice. Design/methodology/approach The study is realized as a combination of a literature review and by the means of analyzing the practices on an industry leader in manufacturing and maintenance services. Findings This research provides a general understanding over data management challenges in e-maintenance and summarizes their associated proposed solutions. In addition, this paper lists and exemplifies different types and sources of data which can be collected in e-maintenance, across different organizational levels. Analyzing the data management practices of an e-maintenance industry leader provides a conceptual approach to address identified challenges in practice. Research limitations/implications Since this paper is based on studying the practices of a single company, it might be limited to generalize the results. Future research topics can focus on each of mentioned data management challenges and also validate the applicability of presented model in other companies and industries. Practical implications Understanding the e-maintenance-related challenges helps maintenance managers and other involved stakeholders in e-maintenance systems to better solve the challenges. Originality/value The so-far literature on e-maintenance has been studied with narrow focus to data and data management in e-maintenance appears as one of the less studied topics in the literature. This research paper contributes to e-maintenance by highlighting the deficiencies of the discussion surrounding the perspectives of data management in e-maintenance by studying all common data management challenges and listing different types of data which need to be acquired in e-maintenance systems.

An exploratory empirical study of whistleblowing and whistleblowers

2020 ◽  
Vol 27 (3) ◽  
pp. 755-770
Author(s):  
Maria Krambia-Kapardis
Keyword(s):  
Statistical Analysis ◽  
Design Methodology ◽  
Research Topic ◽  
Due Date ◽  
Content Type ◽  
Unethical Behaviour ◽  
Eu Member States ◽  
European Directive ◽  
Original Survey ◽  
Practical Implications

Purpose The purpose of this study is to develop a profile of whistleblowers and to determine whether whistleblowing legislation would encourage those individuals to bring to light some illegal or unethical behaviour that otherwise would remain in the shadows. Design/methodology/approach Having identified whistleblowing correlation, a survey was carried out in Cyprus of actual whistleblowers and could-have-been whistleblowers. Findings Males between 46 and55 years of age, regardless of whether they have dependents or hold senior positions in organizations are significantly more likely to blow the whistle. However, could-have-been whistleblowers did not go ahead because they felt that the authorities would not act on their information. Research limitations/implications Because of the sensitive nature of the research topic and the fact that only whistleblowers or intended whistleblowers could participate in the study, the sample size is limited as a result. This, in turn, limits both the number of respondents in each category (actual and intended) as well as constrains the statistical analysis that could be carried out on the data. Practical implications It remains to be seen whether EU Member States shall implement the European Directive 2019/1937 on the protection of persons who report breaches of Union Law, in its entirety by the due date, namely December 2021. Originality/value This study provides a literature review of whistleblowing and reports an original survey against the backdrop of the European Directive.

How Phillips saw the light

2020 ◽  
Vol 36 (8) ◽  
pp. 29-31
Keyword(s):  
Design Methodology ◽  
Reading Time ◽  
Daily Basis ◽  
Business World ◽  
Content Type ◽  
Freak Show ◽  
The World ◽  
Pertinent Information ◽  
The One ◽  
Practical Implications

Purpose Reviews the latest management developments across the globe and pinpoints practical implications from cutting-edge research and case studies. Design/methodology/approach This briefing is prepared by an independent writer who adds their own impartial comments and places the articles in context. Findings The problem with developing a reputation of being something of an oracle in the business world is that all of a sudden, everyone expects you to pull off the trick of interpreting the future on a daily basis. Like a freak show circus act or one-hit wonder pop singer, people expect you to perform when they see you, and they expect you to perform the thing that made you famous, even if it is the one thing in the world you don’t want to do. And when you fail to deliver on these heightened expectations, you are dismissed as a one trick pony, however good that trick is in the first place. Originality/value The briefing saves busy executives and researchers hours of reading time by selecting only the very best, most pertinent information and presenting it in a condensed and easy-to-digest format.

scholarly journals Examining the accounts of oil spills crises in Nigeria through sensegiving and defensive behaviours

2020 ◽  
Vol 33 (8) ◽  
pp. 2053-2076 ◽  
Author(s):  
Osamuyimen Egbon ◽  
Chijoke Oscar Mgbame
Keyword(s):  
Policy Implication ◽  
Design Methodology ◽  
Oil Spills ◽  
Burden Of Proof ◽  
Multinational Companies ◽  
External Factors ◽  
Content Type ◽  
Political Dynamics ◽  
Defensive Behaviours ◽  
Practical Implications

PurposeThe paper examines how oil multinational companies (MNCs) in Nigeria framed accounts to dissociate themselves from causing oil spills.Design/methodology/approachThe authors utilised data from relevant corporate reports, external accounts and interviews, and used sensegiving with defensive behaviours theoretical framing to explore corporate narratives aimed at altering stakeholders' perceptions.FindingsThe corporations gave sense to their audience by invoking scapegoating blame avoidance narrative in attributing the cause of most oil spills in Nigeria to outsiders (sabotage), despite potentially misclassifying the sabotage-corrosion dichotomy. Corporate stance was reinforced through justifying narrative, which suggested that multi-stakeholders jointly determined the causes of oil spills, thus portraying corporate accounts as transparent, credible and objective.Research limitations/implicationsThe socio-political dynamics in an empirical setting affect corporate accounts and how those accounts appear persuasive, implying that such contextual factors merit consideration when evaluating corporate accounts. For example, despite contradictions in corporate accounts, corporate attribution of oil spills to external factors appeared persuasive due to the inherently complicated socio-political dynamics.Practical implicationsWith compensation to oil spills' victims only legally permitted for non-sabotage-induced spills alongside the burden of proof on the victims, the MNCs are incentivised to attribute most oil spills to sabotage. On policy implication, accountability would be best served when the MNCs are tasked both with the burden of proof and a responsibility to demonstrate their transparency in preventing oil spills, including those caused by sabotage.Originality/valueCrisis situations generate multiple and competing perspectives, but sensegiving and defensive behaviours lenses enrich our understanding of how crisis-ridden companies frame narratives to alter stakeholders' perceptions. Accounts-giving therefore partly satisfies accountability demands, and acts as sensegiving signals aimed at reframing/redefining existing perceptions.

OCIE issues risk alert on the most frequently identified advisory fee and expense compliance issues

2018 ◽  
Vol 19 (4) ◽  
pp. 1-3
Author(s):  
Robert Van Grover
Keyword(s):  
Design Methodology ◽  
Best Practice ◽  
Investment Management ◽  
Content Type ◽  
Informed Decisions ◽  
Policies And Procedures ◽  
The Us ◽  
Investment Advisers ◽  
Practical Implications

Purpose To summarize and interpret a Risk Alert issued on April 12, 2018 by the US SEC’s Office of Compliance Inspections and Examinations (OCIE) on the most frequent advisory fee and expense compliance issues identified in recent examinations of investment advisers. Design/methodology/approach Summarizes deficiencies identified by the OCIE staff pertaining to advisory fees and expenses in the following categories: fee billing based on incorrect account valuations, billing fees in advance or with improper frequency, applying incorrect fee rates, omitting rebates and applying discounts incorrectly, disclosure issues involving advisory fees, and adviser expense misallocations. Findings In the Risk Alert, OCIE staff emphasized the importance of disclosures regarding advisory fees and expenses to the ability of clients to make informed decisions, including whether or not to engage or retain an adviser. Practical implications In light of the issues identified in the Risk Alert, advisers should assess the accuracy of disclosures and adequacy of policies and procedures regarding advisory fee billing and expenses. As a matter of best practice, advisers should implement periodic forensic reviews of billing practices to identify and correct issues relating to fee billing and expenses. Originality/value Expert guidance from experienced investment management lawyer.

“Please tidy up before leaving”: nudging Airbnb guests toward altruistic behavior

2019 ◽  
Vol 13 (4) ◽  
pp. 524-530 ◽  
Author(s):  
Paul Ranson ◽  
Daniel Guttentag
Keyword(s):  
Social Presence ◽  
Design Methodology ◽  
Field Experiments ◽  
Experimental Results ◽  
Altruistic Behavior ◽  
Content Type ◽  
The Social ◽  
Relationship Model ◽  
Social Market ◽  
Practical Implications

Purpose This study aimed to investigate whether increasing the social presence within an Airbnb lodging environment could nudge guests toward altruistic cleaning behaviors. Design/methodology/approach The study was based around a theoretical framework combining the social-market versus money-market relationship model, nudge theory and social presence theory. A series of three field experiments were conducted, in which social presence was manipulated to test its impact on guest cleaning behaviors prior to departure. Findings The experimental results confirmed the underlying hypothesis that an Airbnb listing’s enhanced social presence can subtly induce guests to help clean their rental units prior to departure. Originality/value This study is the first to examine behavioral nudging in an Airbnb context. It is also one of the first field experiments involving Airbnb. The study findings offer clear theoretical and practical implications.

Sign in / Sign up

Export Citation Format

Share Document