Search results

Mouth segmentation is one of the challenging tasks of development in lip reading applications due to illumination, low chromatic contrast and complex mouth appearance. Recently, deep learning methods effectively solved mouth segmentation problems with state-of-the-art performances. This study presents a modified Mobile DeepLabV3 based technique with a comprehensive evaluation based on mouth datasets.

This paper presents a novel approach to mouth segmentation by Mobile DeepLabV3 technique with integrating decode and auxiliary heads. Extensive data augmentation, online hard example mining (OHEM) and transfer learning have been applied. CelebAMask-HQ and the mouth dataset from 15 healthy subjects in the department of rehabilitation medicine, Ramathibodi hospital, are used in validation for mouth segmentation performance.

Extensive data augmentation, OHEM and transfer learning had been performed in this study. This technique achieved better performance on CelebAMask-HQ than existing segmentation techniques with a mean Jaccard similarity coefficient (JSC), mean classification accuracy and mean Dice similarity coefficient (DSC) of 0.8640, 93.34% and 0.9267, respectively. This technique also achieved better performance on the mouth dataset with a mean JSC, mean classification accuracy and mean DSC of 0.8834, 94.87% and 0.9367, respectively. The proposed technique achieved inference time usage per image of 48.12 ms.

The modified Mobile DeepLabV3 technique was developed with extensive data augmentation, OHEM and transfer learning. This technique gained better mouth segmentation performance than existing techniques. This makes it suitable for implementation in further lip-reading applications.

The purpose of this paper is to provide novel insights into arts consumption behaviour and patterns of communication displayed by arts consumers using Peterson’s theoretical framework, and to identify differences in the use of communication channels across arts segments.

The authors conducted an a priori market segmentation study, with two variables serving as segmentation criteria, namely, the frequency of and the variety of arts events attended. The authors tested for differences in communication patterns.

Four segments were created: low-frequency univores, low-frequency multivores, high-frequency multivores and high-frequency omnivores. They differ in their communication patterns and online behaviours, including their online activities before and after attending arts events. Printed materials and e-mail newsletters were the most effective communication channel for raising awareness of all arts consumers.

Understanding these communication patterns can help arts marketers to increase the attendance of low-frequency segments and broaden the variety of arts events attended by the univore and multivore segments. The generalisability of the findings is limited as the survey was conducted among online Australian arts consumers only.

The paper adds the dimension of arts consumption frequency to the taxonomy of omnivores and univores proposed by Peterson, which is based on the variety of consumed arts only. The paper contributes to communication and arts marketing literature by identifying key differences in communication patterns across segments of arts consumers and the most promising communication channels to engage them.

The purpose of this paper is to examine how received word-of-mouth (WOM) influences consumer emotions and, in turn, behavioral attitude and intention.

A conceptual model is developed by extending the theory of reasoned action framework to include WOM and emotions. The conceptual model is operationalized through a structural equation model, and the model is estimated and tested by using the partial least squares method. A survey among 509 consumers in Denmark forms the empirical basis for the study.

The paper finds that positive and negative WOM has an asymmetric influence on emotions, behavioral attitude and intention, i.e. that consumers respond differently to positive and negative WOM. The paper also finds that positive WOM has a larger impact than the social norm on behavioral attitude and intention and that negative WOM has an impact equal to that of the social norm. Furthermore, the study finds that emotions are an important mediator for both WOM and social norm.

The paper is limited to a large travel agency in Denmark.

This paper has clear implications in terms of measuring the importance of WOM and emotions in consumer decision-making. It may serve as a useful basis for a practical WOM marketing strategy, which is a critical and increasingly applied element of customer-focused companies’ marketing strategies.

This paper provides new insights into how WOM works and the interplay between WOM, emotions and social norm in consumer decision-making.

By integrating the diffusion of innovation (DOI) theory, technology acceptance model (TAM), and social capital theory, the purpose of this paper is to: develop a model of consumer behavior and trial willingness toward nano-foods from product, consumer, and social perspectives; examine the effects of innovative features, consumer characteristics, and trust in authority on subjective perceptions (perceived trustworthiness and perceived benefit) as well as the social influence on attitudes toward nano-foods and trial willingness; examine the moderating role of product uncertainty on the relationship between these characteristics and subjective perceptions; and examine the effect of perceived benefit on perceived trustworthiness.

The results of the structural equation model (SEM), with nano-food knowledge data collected from 431 respondents, supported the research model and revealed the main effects hypothesized in this study and the moderating effect of product uncertainty. Simple slope analysis was further adopted to test the significant moderating effects.

The SEM results indicated that innovative characteristics (relative advantage, lack of observability, and novelty), consumer characteristics (perceived technology application), and social characteristics (trust in authority) affect perceived trustworthiness or perceived benefit. Social influence also has a direct effect on attitude toward nano-foods and trial willingness. Product uncertainty significantly moderates the relationship between characteristics (relative advantage and perceived technology application) and subjective perceptions (perceived trustworthiness and perceived benefit).

With increasing numbers and kinds of nanotechnology products now being developed and sold, it is important to go further to determine consumer perceptions and attitudes toward these. This study, thus, applied the DOI, TAM, and social capital theory to examine this issue. However, other theories might also be used to carry out research from other perspectives. This study should, thus, be seen as preliminary, and it is hoped that more works will discuss consumer attitudes toward nanotechnology products in the future.

When a new nano-food is introduced, the current study suggests that food manufacturers use the description on the package as a communicative tool. Detailing the advantages of nano-foods on food packages might be a useful way to enhance trial willingness and to reduce the fears and insecurities related to the use of nano-related products. In addition, if food manufacturers could cooperate with organizations or individuals seen as having some authority in this area (e.g. nanotechnology researchers) in order to disseminate accurate information about nanotechnology and related food products, this might be an effective way to increase sales and profits.

This is the first paper integrating the DOI, the social capital theory and the TAM to empirically investigate consumer willingness to try nano-food products.

The perceived electronic-service quality (e-SQ) has become a relevant research area, not only in developed but also in smaller, less-developed countries. The purpose of this paper is to provide a description of an analysis into the relationship of the dimensions of perceived e-SQ and satisfaction as well as WOM intention in case of an online bookstore in Hungary where technical development and internet penetration is emerging; however, it is developing from an economic perspective. Beyond this a potential segmentation is introduced in the Hungarian market.

The direct effect of perceived e-SQ’s dimensions on satisfaction and on traditional WOM were analysed using the PLS-SEM method, which was followed by the segmentation approach. The paper also demonstrates differences of the identified consumer segments, using multivariate analysis of variance.

According to the research only the dimension of efficiency and responsiveness have a significant positive effect on satisfaction, and beside these the quality perception of fulfilment has a significant influence on WOM intention. Using the relevant latent variable scores segmentation was conducted and four clusters were identified.

Due to peculiarities of e-services, quality measurement needs a constant revision and adoption. Extent amount of research has been dedicated to analyse the relationship of quality and satisfaction, but the direct effect of relevant quality dimensions on word-of-mouth intention is a new research field. Segmenting customers based on latent variable scores of the proposed model has not been conducted before in case of an online bookstore in Hungary. According to the results the evaluation of the technology-based components has the greatest effect on satisfaction and WOM intention. However, web-shops managers should focus not only on online characteristics but also on offline, human-based interactions and the service quality of their delivery partners.

The coupling process between the loading mechanism and the tank car mouth is a crucial step in the tank car loading process. The purpose of this paper is to design a method to accurately measure the pose of the tanker car.

The collected image is first subjected to a gray enhancement operation, and the black parts of the image are extracted using Otsu’s threshold segmentation and morphological processing. The edge pixels are then filtered to remove outliers and noise, and the remaining effective points are used to fit the contour information of the tank car mouth. Using the successfully extracted contour information, the pose information of the tank car mouth in the camera coordinate system is obtained by establishing a binocular projection elliptical cone model, and the pixel position of the real circle center is obtained through the projection section. Finally, the binocular triangulation method is used to determine the position information of the tank car mouth in space.

Experimental results have shown that this method for measuring the position and orientation of the tank car mouth is highly accurate and can meet the requirements for industrial loading accuracy.

A method for extracting the contours of various types of complex tanker mouth is proposed. This method can accurately extract the contour of the tanker mouth when the contour is occluded or disturbed. Based on the binocular elliptic conical model and perspective projection theory, an innovative method for measuring the pose of the tanker mouth is proposed, and according to the space characteristics of the tanker mouth itself, the ambiguity of understanding is removed. This provides a new idea for the automatic loading of ash tank cars.

The purpose of this paper is to examine whether a priori segmentation of visitors to a large urban destination along the dimensions of gender, place of residence (domestic, former states, and international), and trip purpose (business, leisure, and VFR) is indeed commonsense for the city's DMO. Specifically, the study investigated whether gender, place of residence, and trip purpose are associated with tourists’ destination risk perceptions, evaluations of destination performance, and post-visitation behavior; that is, intention to revisit and willingness to recommend.

The analysis used data obtained in a 2013 survey of visitors to Nizhni Novgorod, a large urban center in Russia.

The results indicate that place of residence and trip purpose discriminate tourists with respect to selected variables and can serve as segmentation bases for marketing communications about the city to potential target markets.

In view of the mega-sport events to be conducted in Nizhni Novgorod in 2018, alleviating risk perceptions of international tourists and improving their experiences while at the destination are important goals for the city government, tourism planners, and destination marketing organizations.

Segmentation bases of place of residence and trip purpose have rarely been examined in relation to a large multifunctional city, while gender has produced varying results. Thus, the study can add to the segmentation literature in the urban context.

The objective of this study is to analyze the experiences in wine tourism according to narratives shared by the visitors themselves. Furthermore, this study aims to examine the levels of intensity associated with these experiences within a wine destination, considering the segmentation of visitors.

This study uses a mixed-methods approach to analyze data, incorporating a deductive process followed by content analysis. Data collection procedures include a bibliographic review and a data survey conducted through netnography research to analyze 954 visitor reviews on TripAdvisor shared by visitors to Vale dos Vinhedos. Also, statistical analysis is performed to assess whether there are any significant variations in attribute citations among different market segmentation profiles.

The study’s discoveries indicate that there are no significant differences in intensity among profile segments for the dimensions of entertainment, aesthetics, educational and interactions, unlike escapism. The findings reveal that attributes such as “winery,” “wine,” “products and services” and “landscape” are essential for all visitors. In addition, the study shows that social interactions in the wine tourism destination are not as significant as previously assumed.

This research study constitutes a methodological advancement in the field of market segmentation using electronic word-of-mouth data. It provides crucial insights into the experiential nuances of the research locus and the varying degrees of these experiences in relation to visitor segmentation. Additionally, the contributions of this study are not only of theoretical importance but also hold practical implications for market segmentation strategies.

Umrah is a religious ritual that takes place inside the Holy Mosque in Makkah. Umrah can be performed any time during the year; however, performing Umrah in the month of Ramadan is much rewarded. Although the kingdom of Saudi Arabia is hosting this event each year, studies that focus on exploring the Holy Mosque visitor segments are scarce. This study aims to explore and describe the marketing segments of Umrah performers relative to their Umrah experience inside the Holy Mosque of Makkah. Most specifically, this study aims to explore segments of Umrah performers based on their perception of servicescape, hedonic and convenience value and the visitors’ outcome behaviors [i.e. intention to revisit and positive word of mouth (PWOM)].

Mixed-method techniques of data collection [i.e. self-administered questionnaires (n = 278) and short discussions (n = 10)] were used.

Cluster analysis is used for data analysis. The findings revealed four clusters of Umrah performers: real, occasional, rational and passionate performers.

This study is a first attempt to target pilgrims based on their experience with the servicescape during the organized religious event; despite its exploratory nature, it reveals interesting insights that will be useful for managers and scholars. Although the study helps to enrich the existing knowledge on visitors’ experience and proposes some implications for practitioners, it does have some limitations. First, convenience sampling was used, and hence the findings cannot be generalized. Second, the limited period of observation did not allow the authors to provide a complete picture of the pilgrims’ behavior; for this reason, the study findings partially describe the phenomenon. Another limitation is related to the difficulty of approaching respondents from Asia or South East Asia although they constitute a significant percentage of the total Umrah performers every year; this is because of the language barrier as data was collected from only English and Arabic speakers. Hence, to overcome these limitations, it is suggested that future studies could be expanded to target Asian respondents and perhaps other nationalities; and could be undertaken in other religious contexts. Moreover, an interesting future study could be carried out to compare the same model during other religious events. Added to that, another growing area of research could be approached by researchers, such as the impact of pilgrims sharing their experiences on influencing E-PWOM.

The findings reveal several implications for policymakers and stakeholders. The segmentation of Umrah performers assists destination managers, policymakers and local firms involved in managing this mass event to identify effective marketing decision-makers, business strategies and policymakers to satisfy the needs of these visitors (Disegna et al., 2011). Particularly, the identification of the key characteristics of these visitors can help destination marketers to develop a marketing mix that suits the needs of each cluster (Smith et al., 2014). Despite that the performers’ main motivation is the religious purpose, marketing strategists can attract the attention of these visitors to visit other religious, cultural and heritage sites in the country.

Encouraging the visit to other tourist spots in Saudi has several impacts on nourishing the economy and the community. Tourism in Saudi could encourage entrepreneurs to start new ventures to satisfy the need of visitors to the country. Small-medium enterprises could benefit from tourism as they could target market niches in which leader companies are not serving. For instance, hand-made souvenirs are one of these industries that could grow to satisfy the need of visitors.

The results contribute to the literature of event segmentation by identifying visitors’ profiles to rarely investigated destinations. The findings reveal several implications for policymakers and stakeholders.