Multimedia Content Research Articles

Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image and Video Forgeries

This paper introduces a hybrid architecture combining Long Short-Term Memory (LSTM) networks and an encoderdecoder model for the detection and localization of image and video forgeries. The proposed system leverages resampling features and LSTM cells to identify manipulation patterns such as splicing and retouching in multimedia content. By utilizing a combination of spatial and temporal features, the model achieves high precision in detecting forged regions. Extensive testing on diverse datasets demonstrates the robustness of the proposed method.

Get Peace of Mind with Do-It-Yourself Living Wills: The Digitalisation of Medical-Legal Practice and the New Post-Covid 19 Approach

“The automatisation of the core tasks performed by legal practitioners […] is an ongoing and open-ended process” (Schäfke-Zell & Asmussen, 2019, p. 65). “A host of innovative legal-tech companies have entered the market of legal service providers, presently challenging the lawyers’ monopoly over the practice of the law, and ultimately, altering the mode of production in the legal field” (Caserta, 2020, p. 1). Beginning with these assumptions, this study draws on ongoing research on healthcare powers of attorney, living wills, and advance directives (Giordano, 2019, 2021) and will explore the current radical changes and restructuring of modalities of production in medical-legal documents and in the delivery of legal services. The legal websites in the corpus under investigation provide guidance in creating a personal living will according to well-established legal procedures that are pursuant to the laws and regulations of a particular state or country. Living wills and advance directives are signed documents in which the declarants state whether or not they wish to be kept alive using artificial means in the event a doctor declares their death to be imminent. Doctors and medical practitioners are legally bound to follow these directives. Following the increased digitalization of the legal field, these documents are now frequently drafted and completed online, thus embracing the full potential of the new technologies available today. Both verbal and visual rhetoric (Murray, 2014; Sherwin, Feigenson, & Spiesel, 2005) will be investigated to ascertain whether and to what extent digital transformation is redefining the ways in which this legal service is offered, thus promoting greater understanding and wider knowledge of a controversial issue such as making decisions regarding one’s end of life and the choices available among various life-prolonging measures and treatments. The research aims to determine whether the new digital genres can help translate the specific constraints and demands of legal argumentation into new popular, cultural and technological discourse which better appeals to peoples’ emotions and values. The legal sector’s increasing use of digital forms and templates embellished with visual and multimedia content may at once have a commodifying and democratizing effect. Legal meanings and services in the new legal market (Schäfke-Zell & Asmussen, 2019, p. 66) might be better understood and internalized, thus reinforcing and disseminating the emerging vernacular of digital culture along with law, regulations and legal institutes and instruments, which would otherwise be difficult for a layperson to comprehend or accept (Anesa, 2016; Calsamiglia, 2003; Calsamiglia & van Dijk, 2004). In addition to this process of democratization of new media, the Coronavirus pandemic also contributed to changing people’s approach to life (Garzone, 2023) and to living wills, triggered by an increased sense of precariousness of life and imminence of death. English-speaking countries, in particular, have seen a surge in people updating and altering advance directives as a result of the complications caused by the disease; different steps might be taken now, when current documents may be dangerously inadequate. The best ways to update existing texts to the new post-Covid 19 conditions therefore call for thorough investigation.

Empowering Student Transition and Engaging Students Using Actionbound: A Gamified Collaborative Community Learning Platform

Transition to University is a significant milestone for students who are embracing new experiences and challenges. It is particularly vital for international students who have to adapt to a new and different learning environment in the UK. Successful transition and sense of belonging in a new institution lay foundation for students’ academic success. However, transition is a process rather than an event. Accordingly, fostering a collaborative community learning environment and facilitate peer networks and community support becomes critical. It enables social interactions and active learning by engaging students in collaborative group activities, which would in turn support students’ transition to and belonging in a new learning environment. With the advancement of technology, computer-assisted and computer-supported collaborative learning flourished in 21st century. The emergence of mobile digital technology leads to the design of gamification in learning, known as game-based learning or gamified collaborative community learning in order to engage students in fun and interactive activities. ‘Actionbound’ is one of the versatile gamification platforms and mobile apps which can engage students in collaborative community learning with gamified activities. It enables users to create, share and participate in interactive scavenger hunts, tours, games and quizzes. It allows users to design custom challenges, incorporate multimedia content and track players’ progress in real-time. It engages participants to work collaboratively to solve challenges and complete tasks. At UHBS, we have used Actionbound to support the student transition into the University’ learning journey at the start of term. We used scavenger hunt game and quiz functions within Actionbound to direct students to collaborate in teams to solve the challenges and tasks. In this action research, students found Actionbound fun and loved the competitive nature with points and leaderboards. It helped them build network and form friendship. Together, they solved puzzles and tackled challenges which supported their transition and got them prepared for learning in a new environment. Moving forward, as an ongoing action research, we would like to extend the use of Actionbound to term time and in module delivery so to track students’ engagement with the collaborative learning platform and investigate the impact on their academic performance.

Advancing radiology education for medical students: leveraging digital tools and resources

This study evaluates diverse educational resources to address the gaps in diagnostic radiology education for medical students, aiming to identify tools that enhance theoretical knowledge and practical diagnostic skills. Employing a multi-faceted review, we analyzed digital platforms, academic databases, and social media for resources beneficial to medical students in radiology, assessing their accessibility, content quality, and educational value. Our investigation uncovered a broad spectrum of resources, from foundational platforms to advanced simulation tools, varying in their approach to teaching radiology. Traditional resources provide essential theoretical knowledge, while digital tools, including interactive case studies and multimedia content, offer immersive learning experiences. Notably, resources integrating machine learning and social media facilitate dynamic, peer-to-peer learning and up-to-date case discussions. Despite the minimal current focus on VR, its role in enhancing interactive learning is notable. The diversity in educational tools highlights the evolving nature of radiology education, reflecting a shift towards more engaging and practical learning methodologies. Identifying and integrating a variety of educational resources into radiology education can significantly enhance learning outcomes for medical students, preparing them for the complexities of modern diagnostic radiology with a well-rounded educational approach.

A Compressed Domain Robust Video Watermarking Resists Geometric Attack

The widespread utilization of mobile devices and the proliferation of video content, facilitated by communication networks, has unfortunately led to issues such as data piracy, illegal usage, and unauthorized sharing. To address these challenges, digital watermarking emerges as a crucial tool, serving purposes such as authentication, maintaining integrity, and identifying rightful owners. In the realm of video watermarking, two primary categories exist: watermarking in the compressed domain and watermarking in the uncompressed domain. Compressed domain watermarking involves expedited data processing through partial video decoding, whereas uncompressed domain watermarking requires more time. This article proposes a novel video watermarking methodology designed specifically to withstand geometric attacks. The proposed method aims to dynamically embed watermarks within video content, thereby enhancing resilience against various geometric distortions. Geometric attacks, including scaling, rotation, cropping, and translation, pose significant challenges in digital watermarking and are thus a focal point of this research. The objective is to integrate this approach with complex video coding standards, leveraging compression domain techniques to fortify resistance against geometric attacks. Tests show that the suggested video watermarking system works well. Not only does it excel in safeguarding against geometric attacks, but it also mitigates perceptual quality degradation, thus ensuring a balance between robustness and visual fidelity. As the prevalence of video content continues to grow, robust watermarking techniques like the one presented here play a vital role in preserving intellectual property rights and ensuring the integrity of multimedia content in the digital age.

Toward comprehensive short utterances manipulations detection in videos

AbstractIn a landscape increasingly populated by convincing yet deceptive multimedia content generated through generative adversarial networks, there exists a significant challenge for both human interpretation and machine learning algorithms. This study introduces a shallow learning technique specifically tailored for analyzing visual and auditory components in videos, targeting the lower face region. Our method is optimized for ultra-short video segments (200-600 ms) and employs wavelet scattering transforms for audio and discrete cosine transforms for video. Unlike many approaches, our method excels at these short durations and scales efficiently to longer segments. Experimental results demonstrate high accuracy, achieving 96.83% for 600 ms audio segments and 99.87% for whole video sequences on the FakeAVCeleb and DeepfakeTIMIT datasets. This approach is computationally efficient, making it suitable for real-world applications with constrained resources. The paper also explores the unique challenges of detecting deepfakes in ultra-short sequences and proposes a targeted evaluation strategy for these conditions.

Accessibility Challenges of Using Podcasts and Vodcasts in a South African Distance Learning University

Academic writing presents a range of challenges for students, particularly those enrolled in distance university institutions. These challenges encompass various facets such as understanding citation and referencing, developing a distinctive writer’s voice, mastering academic discourse, paraphrasing, summarising, and adhering to academic conventions. Notably, deficiencies in academic writing skills often trace back to inadequate preparation during high school education, potentially leading to qualification deferment and high dropout rates. To tackle these challenges, podcasts and vodcasts emerged as essential tools to bridge academic gaps, catering to diverse learning styles and offering flexibility beyond traditional teaching methods. However, the efficacy of supplemental multimedia tools warrants exploration, considering uncertainties regarding student acceptance. Thus, this study aimed to identify accessibility challenges, to reduce existing barriers and enhance accessibility in open distant institutions. Utilising qualitative research methodologies, including focus group discussions and literature analysis, data collection was conducted. The study drew upon Moore’s theory of transactional distance and Garrison et al.’s community of inquiry framework to create collaborative online interactions and meaningful lecturer-student engagement, culminating in the construction of new knowledge. Findings revealed that students did not encounter accessibility challenges and expressed preference for shorter podcasts and vodcasts. These multimedia formats alleviated boredom, clarified complex concepts, prevented monotony, enhanced attention and comprehension, stimulated interest, facilitated active learning, and accommodated various learning styles. Podcasts and vodcasts reduced transactional distance and created a sense of community. Contrary to prevailing literature, students did not encounter accessibility challenges, shifting the focus towards shorter, high-quality multimedia content rather than accessibility concerns.

Feature-level Fusion vs. Score-level Fusion for Image Retrieval Based on Pre-trained Deep Neural Networks

Today’s complex multimedia content made retrieving images similar to the user’s query from the database a challenging task. The performance of a Content-Based Image Retrieval System (CBIR) system highly depends on the image representation in a form of low-level features and similarity measurement. The traditional visual descriptors that do not provide good prior domain knowledge could lead to poor performance retrieval results. On the other hand, Deep Convolutional Neural Networks (DCNNs) have recently achieved a remarkable success as methods for image classification in various domains. Recently, pre-trained deep convolution neural networks on thousands of classes have the ability to extract very accurate and representative features which, in addition to classification, can also be successfully used in image retrieval systems. ResNet152, GoogLeNet and InceptionV3 are some of the effective and successful examples of pre-trained DCNNs recently applied in a computer vision tasks such as object recognition, clustering, and classification. In this paper, two approaches for a CBIR system, namely early fusion and late fusion, have been presented and compared. The early fusion utilizes concatenation of the features extracted by each possible pair of DCNNs, that is ResNet152-GoogLeNet, ResNet152-InceptionV3, and GoogLeNet-InceptionV3, and the late fusion apply CombSum method with Z-Score standardization to combine the score results provided by each DCNN of the aforementioned pairs. In the experiments on a popular WANG dataset it has been shown that late fusion approach slightly outperforms early fusion approach. The best performance of our experiments in terms of Average Precision (AP) for the top 20 results reaches 96.82%.

Analysis of Influencer Marketing on Social Media Platforms

Influencer marketing is a key factor of organisation advertising and marketing techniques, driven by the sizable use of social media platforms. This research was carried out to examine the determining factors and effect of influencer advertising and marketing on social media structures. We analyzed information accumulated from various social media channels to apprehend the impact of metrics together with likes, remarks, and stocks on logo communique. We additionally utilized social community evaluation to become aware of Key Opinion Leaders (KOLs) and carried out text and multimedia content analysis to delve deeper into the outcomes of content. The consequences display considerable differences in affect factors throughout systems, highlighting the need for tailor-made influencer advertising techniques. This take a look at contributes to the literature on influencer advertising and marketing and offers valuable insights for groups aiming to conduct centered social media advertising.

The Role of e-Learning During Martial Law: The Ukrainian Experience

The research aim is to reveal the role of e-learning during Martial law by the example of Ukrainian experience. It focuses on the following objectives: to outline the advantages and challenges of e-learning; to describe the peculiarities of implementation of e-learning at the different levels of education; to analyse teaching methods used to integrate e-learning; and to develop the recommendations to implement e-learning. The systemic literature review was carried out to provide an objective summary of the current topic. All sources were published between March, 2022 and May, 2024. The literature focused on e-learning in Ukraine or similar conflict-affected areas. All articles were available in English or Ukrainian. To analyse the data, the synthesis method was applied. The findings proved that e-learning became an important tool during emergencies, providing continuity in education. It was explained that e-learning is introduced at primary, secondary, and higher levels of education. It includes synchronous and asynchronous models. Certain teaching methods are used to implement e-learning effectively. They relate to interactive simulations, multimedia content, gamification, discussion forums, and personalized learning. These methods, combined, create a dynamic e-learning environment that enhances students’ educational outcomes, particularly during emergencies. The implementation of e-learning in Ukraine during Martial law requires careful consideration of the recommendations: enhancement of digital infrastructure, adoption of flexible learning, formation of digital literacy, support of mental health, using interactive methods, increase of content quality, regular assessment, encouragement of positive teacher-student interaction, implementation of adaptive learning tools, and protection of students and educators' data. The research outcomes on the role of e-learning during Martial law can be used for the development of strategic plan of implementation of e-learning tools within the learning process in the regions affected by war or other emergencies. Also, the study can contribute to future educational practices, encouraging the development of more innovative learning solutions.

Penerapan Teknologi Augmented Reality sebagai Media Pembelajaran Komponen Elektronika: Mata Kuliah Elektronika Dasar

This study aims to apply Augmented Reality (AR) technology as a learning media for electronic components using Android. Augmented Reality technology is growing rapidly and is used in various fields such as education. By using Android devices as a platform, users can integrate Augmented Reality into applications that can be used for the introduction of electronic components, by pointing the camera to the marker in the application, augmented reality and information about the function of the electronic component will appear. In this study, the authors used the Multimedia Development Life Cycle (MDLC) method which is a structured approach to designing, developing, and releasing creative and effective multimedia content. In the research that has been done, the results obtained are augmented reality applications for the introduction of android-based electronic components.

Lazer Boa Vista: Web Application of Leisure Spaces in Boa Vista/Roraima

Objective: The main objective of this study was to explore and identify the main leisure spaces in Boa Vista/Roraima, and to develop a web application that allows users to access interactive multimedia content with the information researched about the municipality (leisure spaces, equipment and activities). Theoretical Framework: The concept of leisure has changed over the years and is currently defined as moments of fun and relaxation in one's free time from work. Providing accurate and up-to-date information on leisure spaces enables people to access and occupy them quickly. Method: This study is characterized by exploratory research and applied research, as its purpose was to generate a product. After the exploratory research, the neighborhoods with the greatest potential for leisure spaces were defined to make up the web application. Leisure research tools were used (bibliographic and documentary research) and application development tools (the programming language suited to the application's purpose). Results and Discussion: 28 neighborhoods with preserved leisure spaces were found, including 25 types of leisure equipment and 45 types of leisure activities practiced in these spaces. This information was used to create the “Lazer Boa Vista” web application. Originality/Value: This study contributes by gathering and listing the leisure spaces in the municipality of Boa Vista/RR. The relevance of this study stands out for highlighting tourist leisure spaces, collaborating with this area socio-economically, popularizing and disseminating them through digital marketing.

MeST-Former: Motion-enhanced Spatiotemporal Transformer for generalizable Deepfake detection

The rise of Deepfake technology has sparked significant concerns due to its potential for misuse and malicious manipulation of multimedia content. Various detection approaches aimed at detecting Deepfake videos have been proposed, mostly relying on the identification of spatial and temporal artifacts. However, due to the different contexts of source images and the variety of generation techniques, current Deepfake detection methods usually perform well on training datasets, and yet generalize poorly to those unseen identities in new datasets. This issue is widely known as the generalization challenge of Deepfake detection. To address this challenge, this paper proposes an advanced spatiotemporal Deepfake video detector, named Motion-enhanced Spatiotemporal Transformer (MeST-Former). MeST-Former is based on the spatiotemporal modeling capacity of the video Swin Transformer. The spatial and temporal features are obtained from the RGB and motion images, respectively. To enhance the generalization ability of MeST-Former to unseen identities in unseen datasets, the ID-related components in the spatial and temporal features are detached. Specifically, MeST-Former adopts the newly proposed Identity-Decoupling Attention (IDC-Att) module to disentangle the ID-related and ID-unrelated components. Only the ID-unrelated components are used to construct more generalizable spatiotemporal representations. This process makes the constructed spatiotemporal features identity-agnostic and more generalizable to unseen identities. We conducted extensive experiments to evaluate the performance of the MeST-Former. Our results indicate that MeST-Former achieves accurate and generalizable Deepfake detection performance. Notably, MeST-Former also demonstrates high efficacy in detecting AI-animated talking-head videos.

Content-Based Image Retrieval and Feature Extraction: Analysing the Literature

A significant amount of multimedia data consists of digital images, and multimedia content analysis is used in many real-world computer vision applications. Multimedia information, especially photos, has become much more complicated in the last several years. Every day, millions of photos are posted to various websites, such as Instagram, Facebook, and Twitter. Finding a suitable image in an archive is a difficult research subject for the field of computer vision. Most search engines use standard text-based techniques that depend on metadata and captions in order to fetch photos. Over the past 20 years, a great deal of research has been conducted on content-based image retrieval (CBIR), picture categorization, and analysis. In image classification models and CBIR, high-level picture representations are represented as feature vectors made up of numerical values. Empirical evidence indicates a considerable disparity between picture feature representation and human visual understanding. Reducing the semantic gap between human visual understanding and picture feature representation is the aim of this study. This study aims to do a thorough analysis of the latest advancements in the domains of Content-Based picture Retrieval and picture representation. We performed a comprehensive analysis of many models for image retrieval and picture representation, encompassing the most recent advancements in semantic deep-learning methods and feature extraction. This paper provides an in-depth analysis of the key ideas and important studies related to image representation and content-based picture retrieval. In an effort to stimulate more research in this field, it also offers a preview of potential future study topics.

Effects of Kahoot! on K-12 Students’ Mathematics Achievement and Multi-Screen Addiction

Digital platforms are increasingly prevalent among young students in K-12 education, offering significant opportunities but also raising concerns about their effects on self-assessment and academic performance. This study investigates the effectiveness of Kahoot! compared to traditional instructional methods in enhancing mathematics achievement and its impact on multiple screen addiction (MSA) among Greek students aged 9 to 12 during a STEM summer camp. A quasi-experimental design was employed with a purposefully selected sample of one hundred and ten (n = 110) students, who were non-randomly divided into two groups: (a) an experimental group of fifty-five students (n = 55) who engaged with Kahoot! (using dynamic visual aids and interactive content) and (b) a control group of fifty-five students (n = 55) who received traditional instruction (using digital textbooks and PowerPoint slides with multimedia content) on laptops and tablets. The findings revealed a statistically significant difference in MSA scores, with the experimental group exhibiting lower MSA scores compared to their counterparts, indicating a positive impact on reducing screen addiction levels. While Kahoot! led to lower MSA levels, it significantly improved overall mathematical achievement, with a substantial effect size, suggesting a strong positive impact on learning outcomes. The current study highlights the importance of aligning educational tools with the intended outcomes and recommends further research to explore the broader impact of gamified learning on student engagement, screen addiction, and learning outcomes.

A threefold chaotic image encryption technique for efficacious image data protection

With the profound use of digital contents in education and social media, multimedia content have become a prevalent means of communication and with such rapid increase, information security is still a major concern. This paper provides a summary of the techniques of securing image data focusing primarily on encryption. This paper additionally also explores the contribution of chaos theory in the domain of image encryption and applies a threefold chaotic map sequence to design an image encryption technique. This chaos-based encryption technique renders characteristics like sensitivity, determinacy, and ergodicity, and hence provides a better trade-off between security and computational speed. The efficacy of proposed algorithm is also evaluated based on well-known statistical metrics like Number of Changing Pixel Rate (NPCR), Unified Average Changing Intensity (UACI), Information Entropy, local Entropy, Correlation analysis, key sensitivity analysis, and NIST Randomness test. Furthermore, the key sensitivity analysis is also discussed which is a major part of any encryption algorithm analysis.

EFFECTIVE PEDAGOGICAL STRATEGIES FOR DIGITAL LEARNERS

This study investigated the effectiveness of various pedagogical strategies in digital learning environments, focusing on blended learning, gamification, adaptive learning technologies, interactive multimedia content, and frequent feedback. Employing a mixed-methods approach, the research combined quantitative surveys and qualitative interviews with students and educators to assess the impact of these strategies on engagement, motivation, and academic performance. The results revealed that blended learning enhances flexibility and personalization, gamification increases motivation through interactive elements, and adaptive technologies tailor content to individual needs. Interactive multimedia content improves retention and understanding of complex concepts, while frequent feedback supports continuous learner development. The findings emphasized integrating diverse pedagogical strategies to optimize digital education and address varying learner needs. Future research should explore the long-term impacts of these strategies, emerging technologies, and their effectiveness across different educational contexts to ensure equitable and compelling learning experiences. KEYWORDS: blended learning, gamification, adaptive learning technologies, multimedia content, frequent feedback, digital learning, educational technology

Modeling Android Security Vulnerabilities: Insights from Statistical Distributions

Android operating system is a mobile operating system that supports multimedia features. Android offers a wide range of applications and integrated features for playing, recording, editing and sharing audio, video, images and other multimedia content. Most Android devices include cameras, speakers, microphones, and other multimedia components. In software security, vulnerabilities are critical concerns that often emerge during software development. Predicting these vulnerabilities post-release is essential for risk assessment and mitigation. While various models have been explored, the Android operating system remains relatively uncharted. This study delves into modeling Android security vulnerabilities using different statistical distributions, comparing their suitability to the widely-used Alhazmi-Malaiya Logistic (AML) model. Data from the National Vulnerability Database (NVD) spanning 2016 to 2018, along with Common Vulnerability Scoring System (CVSS) scores, was analyzed. The study evaluates several distribution models, including Logistic, Weibull, Nakagami, Gamma, and Log-logistic, for monthly vulnerability counts and average monthly impact values. Goodness-of-fit tests and information criteria were applied for model robustness assessment. The findings offer valuable insights for researchers and Android software developers, aiding prediction, risk assessment, resource allocation, and research direction. Logistic and Nakagami distributions emerged as the best-fit models for average monthly impact values and monthly vulnerability counts, respectively. Finally, statistical methods perform better against known artificial intelligence methods for small data sets or more clearly defined data due to their flexible features such as comprehensibility, amount of data, need for calculation, and data independence.

A novel approach for long-term secure storage of domain independent videos

Long-term protection of multimedia contents is a complex task, especially when the video has critical elements. It demands sophisticated technology to ensure confidentiality. In this paper, we propose a blended approach which uses proactive visual cryptography scheme along with video summarization techniques to circumvent the aforementioned issues. Proactive visual cryptography is used to protect digital data by updating periodically or renewing the shares, which are stored in different servers. And, video summarization schemes are useful in various scenarios where memory is a major concern. We use a domain independent scheme for summarizing videos and is applicable to both edited and unedited videos. In our scheme, the visual continuity of the raw video is preserved even after summarization. The original video can be reconstructed through the shares using auxiliary data, which was generated during video summarization phase. The mathematical studies and experimental results demonstrate the applicability of our proposed method.

Pengembangan Media Pembelajaran Multimedia Interaktif pada Materi Ekologi dan Keanekaragaman Hayati Indonesia untuk Peserta Didik Kelas VII di SMP Negeri 2 Darma

The purpose of this research is to develop and determine the feasibility of interactive multimedia content in science class VII of Indonesia's ecology and biodiversity material. This research uses a Research and Development (R&D) method with a development model called ADDIE. This development model has five phases, namely analysis, design, development, implementation, and evaluation. The sample in this study was taken from 1 (one) class at SMP Negeri 2 Darma which amounted to 25 students. The data collection techniques in this study are observation, interviews, and questionnaires. The end result of this research is the development of products in the form of interactive multimedia content. The development of interactive multimedia was tested through a questionnaire for validation by media experts and obtained a feasibility level of 85% which is included in the "Very Feasible" feasibility level, and material experts realized that they got a feasibility percentage of 92% including the "Very Feasible" category. A small group experiment involving five students of SMP Negeri 2 Darma produced a result of 93% including the "Very Feasible" category. The results of the large group test with a total of 20 students showed a feasibility of 93% including the "Very Feasible" category. The average percentage of results from media experts, material experts, small-scale and large-scale trials got 91% with the category of "Very Feasible"