Search results

Although numerous signal modalities are available for emotion recognition, audio and visual modalities are the most common and predominant forms for human beings to express their emotional states in daily communication. Therefore, how to achieve automatic and accurate audiovisual emotion recognition is significantly important for developing engaging and empathetic human–computer interaction environment. However, two major challenges exist in the field of audiovisual emotion recognition: (1) how to effectively capture representations of each single modality and eliminate redundant features and (2) how to efficiently integrate information from these two modalities to generate discriminative representations.

A novel key-frame extraction-based attention fusion network (KE-AFN) is proposed for audiovisual emotion recognition. KE-AFN attempts to integrate key-frame extraction with multimodal interaction and fusion to enhance audiovisual representations and reduce redundant computation, filling the research gaps of existing approaches. Specifically, the local maximum–based content analysis is designed to extract key-frames from videos for the purpose of eliminating data redundancy. Two modules, including “Multi-head Attention-based Intra-modality Interaction Module” and “Multi-head Attention-based Cross-modality Interaction Module”, are proposed to mine and capture intra- and cross-modality interactions for further reducing data redundancy and producing more powerful multimodal representations.

Extensive experiments on two benchmark datasets (i.e. RAVDESS and CMU-MOSEI) demonstrate the effectiveness and rationality of KE-AFN. Specifically, (1) KE-AFN is superior to state-of-the-art baselines for audiovisual emotion recognition. (2) Exploring the supplementary and complementary information of different modalities can provide more emotional clues for better emotion recognition. (3) The proposed key-frame extraction strategy can enhance the performance by more than 2.79 per cent on accuracy. (4) Both exploring intra- and cross-modality interactions and employing attention-based audiovisual fusion can lead to better prediction performance.

The proposed KE-AFN can support the development of engaging and empathetic human–computer interaction environment.

The purpose of this paper is to demonstrate how mechanistic and organic metaphors might be fused through the application of cultural imagery.

This paper is a theoretical examination of metaphor and its application in public organizations. Specifically, this paper examines the possibility that images from popular culture might offer some insights. Selected metaphors linked by elective methodological affinities are examined in order to determine potential significance of the Robocop metaphor for guiding research in organizations.

The popular culture image Robocop from 1980s films can help us detect what is not being included in most theoretical analyses of public organizations, while simultaneously helping us to purge the negative connotations of the Robocop image.

The popular culture image can help us to understand change in public organizations.

It is one of the few, if any, papers using popular culture images to bridge metaphor and imagery in the study of organizational change.

The purpose of this paper is to explore how people differently create meaning from photos taken by either a lifelogging camera (LC) (i.e. automatic capture) or a mobile phone camera (MC) (i.e. manual capture). Moreover, the paper investigates the different changes in the interpretative stance of lifelog photos and manually captured photos over time to figure out how the LC application could support the users’ iconological interpretation of their past.

A 200-day longitudinal study was conducted with two different user groups that took and reviewed photos taken by either a LC or a MC. The study was structured in two phases: a photo collection phase, which lasted for five days (Day 1‒Day 5), and a three-part semi-structured interview phase, which was conducted on Days 8, 50 and 200.

Results revealed that the interpretative stance of the LC group changed greatly compared to the MC group that kept a relatively consistent interpretative stance over time. A significant difference between the two groups was revealed on Day 200 when the lifelog photos provoked a more iconological and less pre-iconographical interpretative stance. This stance allowed the viewers of lifelog photos to systemically interpret the photos and look back upon their past with different viewpoints that were not recognized before.

This paper contributes to further understand the dynamic change in interpretative stance of lifelog photos compared to manually captured photos through a longitudinal study. The results of this study can support the design guidelines for a LC application that could give opportunities for users to create rich interpretations from lifelog photos.

This paper aims to evaluate trends in research and clinical practice that may contribute to the limited utility of assessment and treatment modalities designed to capture and address psychopathy. It identifies a lack of consistency between the academic understanding of psychopathy and how the construct is applied in clinical contexts. The authors provide clarity and direction for a more effective application of the psychopathy construct in practical contexts.

This review first examines the etiology of important limitations to psychopathy research and practical application, and proposes the adoption of the most recent empirical conceptualization of the construct into practical contexts. It then evaluates the current functionality of psychopathy in practical contexts. The review ultimately proposes a method for designing intervention practices based on the model used in the development of dialectical behavior therapy (DBT) for borderline personality disorder, which will improve the practical utility of the construct.

The present review provides evidence that a multifaceted and dimensional perspective of psychopathy will improve the practical utility of the construct and help move the field forward. It suggests that considering independent components of the psychopathy construct along a continuous scale, as with DBT, will contribute to improvements in assessments and treatments that target psychopathy.

The current review applies relevant research to a model for developing an intervention modality particularly in forensic or correctional settings where individuals high in psychopathy are often seen. The implications outlined provide a framework that could impact practice and assessment in forensic contexts moving forward.

Previous research has not concisely outlined problems concerning the link between psychopathy research and how the construct is applied in practical settings. Few researchers have proposed plausible solutions that could improve the utility of the construct in such settings.

The current study examined police response, specifically identification and arrest decisions, to nonfatal strangulation occurring within the context of intimate partner violence.

Data for the present study were derived from a sample of 117 possible nonfatal strangulation case reported to a police agency located in one of the fifth largest and most diverse US cities. A series of logistic regression models were employed to examine the role of victim, suspect and case characteristics on officer formal identification of strangulation and officer arrest decisions.

Results revealed that 14% of all intimate partner violence (IPV) cases reported to the police agency involved possible nonfatal strangulation and less than half of all possible nonfatal strangulation cases were formally identified as such by officers. The odds of formal identification of strangulation by police increased when strangulation was manual and when victims reported difficulty breathing. Injury and formal identification increased the odds of arrest.

This study is the first to examine predictors of police formal identification and arrest decisions in nonfatal strangulation occurring within intimate partner violence incidents.

This paper claims that the parking policy is one of the most obvious tools for reducing traffic congestion, pollutant emissions and conflicts between transportation network users. The purpose of this paper is to propose and implement a strategy, via a simulation tool, for the sharing of parking places between light cars and vans for goods delivery.

Temporal and spatial dynamic booking of on‐street parking places is described by using the multi‐agent paradigm. Main agents concerned by the sharing of parking places, their rules and interactions are implemented. Behavioral models and learning process of cognitive agents based on stated preferences collected beside the network users are designed for capturing multi‐agent interactions.

By coupling a 2D traffic simulation tool and the Copert III methodology, it is possible to simulate the traffic and environmental consequences of several scenarios for different infrastructures, occupancy rate of the places reserved for goods delivery and durations of the delivery process.

Several points are under development: a 3D environment will capture with more realism the behavior of agents in a larger spatial scale and in real time. The behavioral models will be designed by stated preferences obtained from surveys containing questions coupled with pictures of possible scenarios.

Applied in a real context, the sharing of parking places strategy shows benefits for traffic and for the environment. A decision maker can use this strategy for simulating scenarios, in the context of an urban area in particular.

The paper demonstrates how a simulation tool based on strategy of parking place sharing can satisfy constraints of transportation network users.

Integrating complementary information with high-quality visual perception is essential in infrared and visible image fusion. Contrast-enhanced fusion required for target detection in military, navigation and surveillance applications, where visible images are captured at low-light conditions, is a challenging task. This paper aims to focus on the enhancement of poorly illuminated low-light images through decomposition prior to fusion, to provide high visual quality.

In this paper, a two-step process is implemented to improve the visual quality. First, the low-light visible image is decomposed to dark and bright image components. The decomposition is accomplished based on the selection of a threshold using Renyi’s entropy maximization. The decomposed dark and bright images are intensified with the stochastic resonance (SR) model. Second, texture information-based weighted average scheme for low-frequency coefficients and select maximum precept for high-frequency coefficients are used in the discrete wavelet transform (DWT) domain.

Simulations in MATLAB were carried out on various test images. The qualitative and quantitative evaluations of the proposed method show improvement in edge-based and information-based metrics compared to several existing fusion techniques.

In this work, a high-contrast, edge-preserved and brightness-improved image is obtained by the processing steps considered in this work to get good visual quality.

Teaching effectiveness is essential to student learning, engagement and success. This study aims to identify the perceived teaching effectiveness attributes from the student’s perspective through a pilot study.

A comprehensive literature review identified 6 demographic and 25 teaching effectiveness characteristics. The Kano model was used to gather and analyze the student’s voices. The research validated the survey instrument using Cronbach’s alpha to ensure internal consistency and Chi-square goodness of fit to test the data distribution. Differences in response patterns were analyzed using Fisher’s exact test. Furthermore, the magnitude of the effect between the teaching effectiveness attributes was determined using Cramer’s V test.

This study determined that students perceived 19 attributes as one-dimensional, 3 as indifferent, 2 as attractive and 1 as one-dimensional and attractive. The analysis found differences in response patterns concerning readings and materials, grading rubrics to set assignment expectations and group/teamwork on projects.

As a pilot study, the sample size was small. Additional research should validate the survey using a larger sample. While the study results are specific to the college surveyed, other educators can use the methodology to identify the attributes important to their students.

Categorizing attributes based on the student’s voice enables instructors to focus on attributes that will improve the learning experience.

This research provides a comprehensive methodology for identifying critical teaching effectiveness attributes from the student’s perspective.

The application of digital twins to optimise operations and supply chain management functions is a bourgeoning practice. Scholars have attempted to keep pace with this development initiating a fast-evolving research agenda. The purpose of this paper is to take stock of the emerging research stream identifying trends and capture the value potential of digital twins to the field of operations and supply chain management.

In this work we employ a bibliometric literature review supported by bibliographic coupling and keyword co-occurrence network analysis to examine current trends in the research field regarding the value-added potential of digital twin in operations and supply chain management.

The main findings of this work are the identification of four value clusters and one enabler cluster. Value clusters are comprised of articles that describe how the application of digital twin can enhance supply chain activities at the level of business processes as well as the level of supply chain capabilities. Value clusters of production flow management and product development operate at the business processes level and are maturing communities. The supply chain resilience and risk management value cluster operates at the capability level, it is just emerging, and is positioned at the periphery of the main network.

This is the first study that attempts to conceptualise digital twin as a dynamic capability and employs bibliometric and network analysis on the research stream of digital twin in operations and supply chain management to capture evolutionary trends, literature communities and value-creation dynamics in a digital-twin-enabled supply chain.

The purpose of this study is to detect these reviews’ complex emotions, visualize and analyze them. Movie reviewers’ moviescores and reviews can be analyzed with respect to their emotion content, aggregated and projected onto a movie, resulting in an emotion map for a movie. It is then possible for a moviegoer to choose a movie, not only on the basis of movie scores and reviews, but also on the basis of aggregated emotional outcome of a movie as reflected by its emotion map displaying certain emotion map patterns desirable for the moviegoer.

The authors use the hourglass of emotion model to find the emotional scores of words of a review, then they use singular value decomposition to reduce the data dimension into singular scores. Once, they have the emotional scores of reviews, the authors cluster them by using k-means algorithm to find similar emotional levels of movies. Finally, the authors use heat maps to visualize four dimensions in a figure.

The authors are able to find the emotional levels of movie reviews, represent them in single scores and visualize them. The authors look the similarities and dissimilarities of movies based on their genre, ranking and emotional statuses. They also find the closest emotion levels of movies to a given movie.

The authors detect complex emotions from the text and simply visualize them.