Active Video Research Articles

Effects of eHealth exercise on paediatric suppurative lung diseases: a systematic review and meta-analysis

BackgroundUtilizing information and communication technologies through eHealth in exercise programs could support their delivery and improve clinical outcomes in children and adolescents with chronic suppurative lung diseases (CSLDs). This study aimed to systematically investigate the effects of eHealth exercise programs on clinical outcomes for this population.MethodsFive databases were searched from inception to April 12, 2024. Two researchers independently screened the retrieved results and rated the methodological quality of the included studies using the revised Cochrane Risk of Bias tool for randomized trials and the Risk of Bias in Non-Randomized Studies – of Interventions tool. The quality of evidence was graded using the GRADE approach. A narrative synthesis of findings was performed, and a meta-analysis was conducted to evaluate the effects of eHealth exercise programs on clinical outcomes that had data from ≥2 studies.ResultsSeven studies used eHealth exercise programs through active video games (n=3), videoconferencing (n=3), and a digital spirometer (n=1) lasting from 3 to 12 weeks. Five studies had participants with cystic fibrosis (CF). Results showed a greater improvement in the 6-minute walk test following the intervention compared to the control group; pooled estimate mean difference [37.2 meters (95%CI: 7.91 to 66.48), p=0.013]. Pulmonary function, exercise capacity, balance, peripheral and respiratory muscle strength, and HRQoL were also improved. Still, most studies involved a considerable risk of bias.ConclusionseHealth exercise programs can improve clinical outcomes in children and adolescents with CF. Further research is needed for other pediatric populations with CSLDs and also for comparisons with conventional exercise programs.

Video-Based Plastic Bag Grabbing Action Recognition: A New Video Dataset and a Comparative Study of Baseline Models.

Recognizing the action of plastic bag taking from CCTV video footage represents a highly specialized and niche challenge within the broader domain of action video classification. To address this challenge, our paper introduces a novel benchmark video dataset specifically curated for the task of identifying the action of grabbing a plastic bag. Additionally, we propose and evaluate three distinct baseline approaches. The first approach employs a combination of handcrafted feature extraction techniques and a sequential classification model to analyze motion and object-related features. The second approach leverages a multiple-frame convolutional neural network (CNN) to exploit temporal and spatial patterns in the video data. The third approach explores a 3D CNN-based deep learning model, which is capable of processing video data as volumetric inputs. To assess the performance of these methods, we conduct a comprehensive comparative study, demonstrating the strengths and limitations of each approach within this specialized domain.

Evidence for the advantages of assessing action video game proficiency in addition to gaming experience

Investigations into whether playing action video games (AVGs) benefit other tasks, such as driving, have traditionally focused on gaming experience (i.e., hours played). A potential problem with this approach is that AVG experience only partially indexes the cognitive skills developed via gaming, which are presumably the source of other task benefits. Thus, a focus on experience, instead of gaming proficiency (i.e., skill level), may account for inconsistencies in existing literature. We investigated whether AVG experience or proficiency best predicts performance in simulated driving. We hypothesised that proficiency would better predict driving performance (speed control, lane maintenance, spare cognitive capacity) than experience. One-hundred-and-sixteen participants drove in a simulator and played an AVG (Quake III Arena). Proficiency predicted all aspects of driving performance, while experience only predicted lane maintenance. These findings highlight the benefits of measuring AVG proficiency, with implications for the video games literature, driving safety and the transfer of skill-based learning.

Skeleton-weighted and multi-scale temporal-driven network for video action recognition

Skeleton-weighted and multi-scale temporal-driven network for video action recognition

Effects of Active Video Games Combined with Conventional Physical Therapy on Perceived Functionality in Older Adults with Knee or Hip Osteoarthritis: A Randomized Controlled Trial

Background: Osteoarthritis (OA) leads to functional decline in older adults. This study aimed to evaluate the effectiveness of active video games (AVGs) as a complement to conventional physical therapy (CPT) in improving functional disability. Methods: Sixty participants were randomly assigned to an experimental group (EG, n = 30, 68.7 ± 5.4 years), which received CPT combined with AVGs, or to a control group (CG, n = 30, 69.0 ± 5.5 years), which received CPT alone. Sessions were performed three times a week for ten weeks. Functional disability was assessed using the WOMAC index before, during, and after the intervention. Secondary outcomes included the Global Rating of Change (GRoC), the Minimal Clinically Important Difference, and patient trajectories through functional disability strata. Results: The EG showed progressive improvements in all WOMAC scores, with moderate to large increases by the end of the intervention, while the CG only showed significant changes in the later stages. The EG demonstrated greater improvements in WOMAC pain and the GroC scale (p < 0.05), maintaining most of the gains at follow-up, whereas the CG showed regression. Additionally, the EG had a higher proportion of responders, particularly for pain, while the CG had a predominance of non-responders and adverse responders. In the EG, 70% improved their functional disability stratification compared to 50% in the CG. Conclusion: Integration of AVGs with CPT further improves perceived functional disability in older adults with OA. Future research should explore these findings further.

Extended Reality Gaming for Exercise and Mindfulness Throughout Pediatric Cancer Rehabilitation: Protocol for a Randomized Controlled Trial.

Pediatric patients with cancer have limited options to self-manage their health while they are undergoing treatments in the hospital and after they are discharged to their homes. Extended reality (ER) using head-mounted displays has emerged as an immersive method of improving pain and mental health and promoting health-enhancing physical activity among a variety of clinical groups, but there is currently no established protocol for improving both physical and mental health in pediatric cancer rehabilitation. This phase I, pilot, feasibility randomized controlled trial aims to investigate the potential effects of a 14-week ER program on physical activity participation and indicators of health among pediatric patients with cancer who undergo bone marrow transplantation. An ancillary aim is to evaluate the feasibility of the program through participant engagement. This study includes a 2-arm parallel group design with a 1-group crossover (the control group will start the intervention after a waiting period). Overall, 16 pediatric patients with cancer undergoing rehabilitation (aged ≥8 years) at a children's hospital will be randomly allocated into one of two groups: (1) an immediate start group that undergoes an ER program in the hospital until discharge and then for 8 weeks at home (total duration of approximately 14 weeks), and (2) a waitlist control group that undergoes usual care in the hospital and for 8 weeks at home, before receiving the 8-week home ER program. The program will include active video gaming with rhythmic music exercises as well as mindfulness-based practices using a high-quality app. Home-based programming will include behavioral coaching calls. Physical activity will be measured daily through step counts using a tri-axial accelerometer. Health outcomes will be measured across time and include global health, measured by the National Institutes of Health Patient-Reported Outcomes Measurement Information System (PROMIS) Pediatric Global Health Scale Short Form 7+2, and lung function, measured by a forced expiratory volume using a peak flow meter. Feasibility will be evaluated through participant engagement metrics, such as enrollment, dropout, adverse events, and attendance rates. Descriptive statistics will be obtained for all study variables. Outcomes will be modeled using mixed modeling procedures, and changes in means will be estimated with CIs. The study was funded in February 2024. Recruitment procedures started on June 27, 2024. All data are anticipated to be collected by February 2026. Full trial results are anticipated to be analyzed and submitted for publication by March 2026. The study's anticipated end date is March 31, 2026. This trial tests an accessible remote program for improving both physical and mental health among pediatric patients with cancer. The knowledge obtained from this study will inform the development of a larger trial. ClinicalTrials.gov NCT06298357; https://clinicaltrials.gov/study/NCT06298357. DERR1-10.2196/64879.

Inclusivity is child’s play: pilot study on usability, acceptability and user experience of a sensory-motor PC game for children with cerebral palsy (GiocAbile)

BackgroundThe use of video games in rehabilitation settings is gaining increasing popularity. However, the lack of commercial video games suitable for children with disabilities and the disappointing user experience of serious games limit their applicability. The aim of this study was to assess the usability, acceptability and user experience of GiocAbile, an active video game for children with cerebral palsy (CP).MethodsThis multicenter pilot observational study was conducted from May to September 2022 at the participating institutions, and enrolled school-aged children affected by CP. Enrolled children played GiocAbile in single-player mode for one hour. The gaming experience was evaluated through self-assessment questionnaires. Non-parametric correlation analysis was conducted to examine the influence of motor and cognitive abilities (GMFCS, MACS, ICF) on declared usability and acceptability.ResultsNineteen children (9.01 ± 1.95 years, 63.1% male) with mild to severe CP were enrolled. The 100% of respondents expressed satisfaction and fulfillment associated with gameplay, with no reports of frustration or disappointment. The 83% would recommend the game to a friend. The controllers were generally deemed easy to use and maneuver, with very few reports of discomfort associated with their use. No correlations were found between usability/acceptability levels and measures of impairment (i.e., GMFCS, MACS, and ICF scales), while cognitive impairment positively correlated with satisfaction during gameplay.ConclusionsGiocAbile is an accessible, user-friendly and enjoyable tool for children with CP, regardless of level of impairment. Based on existing literature, we hypothesize that GiocAbile may improve motivation, participation, and rehabilitation outcomes in children with CP, although further studies are needed to confirm our hypothesis.

Developing Talented Children’s Computational Thinking Through Multimodal Literacies in Pop-Up Storybooks: A Case Study in Hong Kong

Computational thinking (CT) currently has been mainly explored using programming robots and conducted in K12 education. In early childhood education, arts have a significant place in children’s learning, expression and cognitive development. Specifically, creating pop-up storybooks is a child-friendly activity. Our study aimed to explore the combination of CT and art, and to develop talented children’s CT abilities through a multimodal literacies educational approach, which referred to using different skills (i.e., writing, drawing, making, and storytelling) in the art activity. A total of 12 talented children were selected to participate in a pop-up storybook production workshop using a convenience sampling method. We adopted an observation method to capture talented children’s CT behaviors, generating a total of 180 min of activity videos and collecting fieldnotes and the children’s worksheets and artworks for the data analysis. Based on a content analysis, we found that talented children enhanced their CT development in multiple modes and practiced seven CT skills. In conclusion, our study emphasizes the importance of art in children’s education and provides new insights for subsequent research on children’s CT education.

PELATIHAN ASESMEN IMPLEMENTASI KURIKULUM MERDEKA (IKM) BAGI GURU SEKOLAH DASAR KABUPATEN PROBOLINGGO

of Education Kec. The source and the service team concluded that the problems in the primary school include (1) the teacher's lack of understanding of the Merdeka Curriculum Implementation Assessment, because it is considered only for IPA subjects, (2) the unavailability of supporting book references in the classroom or library related to the assessment of Merdeka Curriculum Implementation, (3) the learning has not been touched by literacy and technology innovations, and (4) Learning in Education The Merdeka Curriculum is still alien to teachers. The solution to this problem is to carry out Focus GroupDiscussion (FGD) activities and training learning activities through the implementation of the Merdeka Curriculum Implementation assessment. Increasing the number of libraries is related to independent curriculum in learning, Independent curriculum learning training, Guidance of evaluation products of training results by teachers. External targets in this activity are to increase teachers' understanding of the concept of independent curriculum implementation assessment, document time schedule based student'activitys, (portfolio), reference book on Independent Curriculum Implementation Assessment for teachers (10 e-books from various sources), publication of activities in 1 mass media and 1 video of activity uploaded on youtube channel, 1 Draft evaluation result assessment of implementation of merdeka curriculum scientific articles in the form of an accredited journal (1 accredited journal article), 1 HKI.

Active Video Games Using Virtual Reality Influence Cognitive Performance in Sedentary Female University Students: A Randomized Clinical Trial.

Virtual reality (VR) is an emerging technology that is proving to be effective in encouraging physical activity (PA) and improving health. Although regular PA has many advantages, physical inactivity continues to be a significant global health concern. Using an ActivPAL for PA assessment, this study examines the effects of an active video game (AVG) using VR on cognitive function among female university students. We randomly divided 44 sedentary female university students (mean age 21.3 years, SD 1.12 years) into two groups, the control group and VR group. During the study period, the VR group was required to play the Beat Saber VR game for 20 min, while the control group was required to remain quiet. Their cognitive performance was evaluated using the Montreal Cognitive Assessment (MoCA)-Arabic version pre- and post-test, and the PA level and intensity were tracked using the ActivPAL. There was a significant difference between the MoCA total score pre-test (mean = 22.3, SD = 2.25) and the MoCA total score post-test (mean = 23.4, SD = 2.48), t (23) = 1.87, p = 0.03. The VR game significantly influenced the naming, abstraction, and orientation components of the MoCA scale (all p ≤ 0.05). The intensity of PA generated by the VR game was equivalent to moderate-to-vigorous PA, with a mean of 4.98 metabolic equivalents of task (MET) (SD = 1.20). The VR game improved the cognitive ability compared to the control group, suggesting that VR games have a positive impact on cognitive function. Physically inactive female university students have been found to benefit from VR games in terms of their cognitive function.

Backdoor Attacks and Defenses Targeting Multi-Domain AI Models: A Comprehensive Review

Since the emergence of security concerns in artificial intelligence (AI), there has been significant attention devoted to the examination of backdoor attacks. Attackers can utilize backdoor attacks to manipulate model predictions, leading to significant potential harm. However, current research on backdoor attacks and defenses in both theoretical and practical fields still has many shortcomings. To systematically analyze these shortcomings and address the lack of comprehensive reviews, this article presents a comprehensive and systematic summary of both backdoor attacks and defenses targeting multi-domain AI models. Simultaneously, based on the design principles and shared characteristics of triggers in different domains and the implementation stages of backdoor defense, this article proposes a new classification method for backdoor attacks and defenses. We use this method to extensively review backdoor attacks in the fields of computer vision and natural language processing, and we also examine the current applications of backdoor attacks in audio recognition, video action recognition, multimodal tasks, time series tasks, generative learning, and reinforcement learning, while critically analyzing the open problems of various backdoor attack techniques and defense strategies. Finally, this article builds upon the analysis of the current state of AI security to further explore potential future research directions for backdoor attacks and defenses.

Learning and Transfer: A Perspective From Action Video Game Play

A growing body of research documents the positive impact that action video game play has on a range of cognitive skills. Such a result, in which training on one task promotes a broad variety of benefits, is a rarity in the cognitive training domain. Instead, the more typical result is that training on one task promotes benefits on that task alone with only limited transfer to untrained tasks. We have proposed that action video game play promotes broad generalization by first enhancing attentional control abilities. This in turn allows for more information to be accrued as one experiences a new task and thus faster learning of that new task. Possible theoretical and practical considerations of such a view are discussed.

ВОЕННАЯ ЖУРНАЛИСТИКА В ЭПОХУ СВО: ОТ ФИКСАЦИИ ФАКТОВ К ОБОБЩЕНИЯМ

The article attempts to identify the main trends in the development of domestic journalism during the SVO period. Although frontline action videos remain the most popular form of factual materials about the SVO today, verbal texts continue to play a fundamentally important role in the work of war correspondents. This is due to both the specific capabilities of the word in reflecting reality and the desire of journalists to generalize information about military life. As a result, one can observe the use of artistic typification and literary cyclization techniques by war correspondents, which should be regarded as a continuation of the classical traditions of Russian literature. These trends are most clearly expressed in the books of essays about the SVO by Alexander Kots “500 Days of Defeats and Victories” and Dmitry Steishin “The Sacred Military Operation”. The comparison of facts from different eras undertaken in the article allows us to identify logically explainable patterns that govern the literary understanding of military operations. At the first stage, individual details and facts are recorded, which find expression in the genre of a documentary essay and other small forms of verbal creativity. The accumulation of facts requires generalizations, which leads, on the one hand, to the use of typification tactics, and on the other hand, to the creation of an essay cycle – a panoramic chronicle of military operations. And finally, the stage of artistic generalization begins, when multiple facts of military reality are transformed into single images – constructed by the author’s imagination, but focusing typical manifestations of reality.

Multi-granularity hierarchical contrastive learning between foreground and background for semi-supervised video action detection

Multi-granularity hierarchical contrastive learning between foreground and background for semi-supervised video action detection

AMS-Net: Modeling Adaptive Multi-Granularity Spatio-Temporal Cues for Video Action Recognition.

Effective spatio-temporal modeling as a core of video representation learning is challenged by complex scale variations in spatio-temporal cues in videos, especially different visual tempos of actions and varying spatial sizes of moving objects. Most of the existing works handle complex spatio-temporal scale variations based on input-level or feature-level pyramid mechanisms, which, however, rely on expensive multistream architectures or explore multiscale spatio-temporal features in a fixed manner. To effectively capture complex scale dynamics of spatio-temporal cues in an efficient way, this article proposes a single-stream architecture (SS-Arch.) with single-input namely, adaptive multi-granularity spatio-temporal network (AMS-Net) to model adaptive multi-granularity (Multi-Gran.) Spatio-temporal cues for video action recognition. To this end, our AMS-Net proposes two core components, namely, competitive progressive temporal modeling (CPTM) block and collaborative spatio-temporal pyramid (CSTP) module. They, respectively, capture fine-grained temporal cues and fuse coarse-level spatio-temporal features in an adaptive manner. It admits that AMS-Net can handle subtle variations in visual tempos and fair-sized spatio-temporal dynamics in a unified architecture. Note that our AMS-Net can be flexibly instantiated based on existing deep convolutional neural networks (CNNs) with the proposed CPTM block and CSTP module. The experiments are conducted on eight video benchmarks, and the results show our AMS-Net establishes state-of-the-art (SOTA) performance on fine-grained action recognition (i.e., Diving48 and FineGym), while performing very competitively on widely used Something-Something and Kinetics.

Peningkatan Literasi Teknologi Guru melalui Pelatihan E-Evaluation Berbasis HOTS di SMAS Muhammadiyah Kota Bima: Dampak pada Efektivitas Evaluasi Pembelajaran

The implementation of E-evaluation based on Higher Order Thinking Skills (HOTS) in private high schools remains limited. Observations from the Community Service Team revealed several issues, including the minimal use of E-evaluation in Muhammadiyah High Schools. Interviews with the principal and several teachers indicated that evaluations are still predominantly paper-based. In 4.0 era, it is essential for both teachers and students to adapt the technological advancements, especially in the evaluation process. E-evaluation serves as an effective tool for assessment at the high school level. The goals of this initiative are to: 1) enhance the technological skills of teachers at partner private schools, 2) improve teachers' understanding of E-evaluation, 3) develop HOTS-based E-evaluation products, and 4) increase teachers’ knowledge about crafting questions that promote Higher Order Thinking Skills. The methods used include presentations, demonstrations, and hands-on practice. The proposed steps for working with teachers are: 1) FDG, 2) training and mentoring, 3) monitoring, and 4) evaluation. The outcomes of this activity include: (1) 90% teacher participation, (2) 80% teachers grasping how to formulate HOTS-based questions, (3) 90% understanding the use of E-evaluation, (4) 90% of students gaining familiarity with courses in Human and Computer Interaction, Teaching Strategies, and Learning Evaluation, (5) the creation of an E-evaluation module/guidebook, (6) certificates for teachers who develop E-evaluation questions, (7) visual materials such as posters, (8) published articles in the Abdi Insani journal, (9) media coverage of activities in online platforms, and (10) activity videos uploaded to the STKIP Taman Siswa YouTube channel. So, the practical significance for teachers is improving the quality of education using E-evaluation Technology in Private schools

Multi-Context Strategies and Opportunities for Increasing Levels of Physical Activity in Children and Young People: A Literature Review.

In today's society, low levels of physical activity are observed in the child and adolescent population, which can cause numerous pathologies, such as obesity and mental health problems. This article aims to compile all the contexts and scenarios where it is possible to increase the levels of daily physical activity of children and young people, and which have significant scientific support. To do so, a literature review was carried out examining four key contexts for intervention: school, extracurricular, family, and socio-community. The results indicate that the school context, with strategies such as physical education classes and active breaks, is crucial but insufficient on its own, so it is essential to complement it with interventions in extracurricular, family, and socio-community environments. The involvement of families, access to adequate infrastructure such as parks and green areas, and the responsible use of technology, including active video games and the role of influencers on social networks, are presented as key elements to combat a sedentary lifestyle. It is important to highlight the importance of establishing socio-educational programs that adopt a comprehensive approach to promote physical activity in children and youth, highlighting the scientific evidence that supports the effectiveness of intervening in multiple scenarios. This review concludes that a coordinated approach between different actors (schools, families, communities) is necessary to ensure that children and youth reach adequate levels of physical activity, which not only improves their physical health, but also their mental well-being and cognitive development.

Connectivity in the Dorsal Visual Stream Is Enhanced in Action Video Game Players.

Action video games foster competitive environments that demand rapid spatial navigation and decision-making. Action video gamers often exhibit faster response times and slightly improved accuracy in vision-based sensorimotor tasks. Background/Objectives: However, the underlying functional and structural changes in the two visual streams of the brain that may be contributing to these cognitive improvements have been unclear. Methods: Using functional and diffusion MRI data, this study investigated the differences in connectivity between gamers who play action video games and nongamers in the dorsal and ventral visual streams. Results: We found that action video gamers have enhanced functional and structural connectivity, especially in the dorsal visual stream. Specifically, there is heightened functional connectivity-both undirected and directed-between the left superior occipital gyrus and the left superior parietal lobule during a moving-dot discrimination decision-making task. This increased connectivity correlates with response time in gamers. The structural connectivity in the dorsal stream, as quantified by diffusion fractional anisotropy and quantitative anisotropy measures of the axonal fiber pathways, was also enhanced for gamers compared to nongamers. Conclusions: These findings provide valuable insights into how action video gaming can induce targeted improvements in structural and functional connectivity between specific brain regions in the visual processing pathways. These connectivity changes in the dorsal visual stream underpin the superior performance of action video gamers compared to nongamers in tasks requiring rapid and accurate vision-based decision-making.

UniBioPAN: A Novel Universal Classification Architecture for Bioactive Peptides Inspired by Video Action Recognition.

The classification of bioactive peptides is of great importance in protein biology, but there is still a lack of a universal and effective classifier. Inspired by video action recognition, we developed the UniBioPAN architecture to create a universal peptide classifier to solve this problem. The architecture treats the peptide sequence as a video sequence and the molecular image of each amino acid in the peptide sequence as a video frame, enabling feature extraction and classification using convolutional neural networks, bidirectional long short-term memory networks, and fully connected networks. As a novel peptide classification architecture, UniBioPAN significantly outperforms other universal architecture in ACC, AUC and MCC across 11 data sets, and F1 score in 9 data sets. UniBioPAN is available in three ways: python script, jupyter notebook script and web server (https://gzliang.cqu.edu.cn/software/UniBioPAN.html). In summary, UniBioPAN is a universal, convenient, and high-performance peptide classification architecture. UniBioPAN holds significant importance in the discovery of bioactive peptides and the advancement of peptide classifiers. All the codes and data sets are publicly available at https://github.com/sanwrh/UniBioPAN.

Comparing conventional and action video game training in visual perceptual learning

Action video game (AVG) playing has been found to transfer to a variety of laboratory tasks in visual cognition. More recently, it has even been found to transfer to low-level visual "psychophysics tasks. This is unexpected since such low-level tasks have traditionally been found to be largely “immune” to transfer from another task, or even from the same task but a different stimulus attribute, e.g., motion direction. In this study, we set out to directly quantify transfer efficiency from AVG training to motion discrimination. Participants (n = 65) trained for 20 h on either a first-person active shooting video game, or a motion direction discrimination task with random dots. They were tested before, midway, and after training with the same motion task and an orientation discrimination task that had been shown to receive transfer from AVG training, but not from motion training. A subsequent control group (n = 18) was recruited to rule out any test–retest effect, by taking the same tests with the same time intervals, but without training. We found that improvement in motion discrimination performance was comparable between the AVG training and control groups, and less than the motion discrimination training group. We could not replicate the AVG transfer to orientation discrimination, but this was likely due to the fact that our participants were practically at chance for this task at all test points. Our study found no evidence, in either accuracy or reaction time, that AVG training transferred to motion discrimination. Overall, our results suggest that AVG training transferred little to lower-level visual skills, refining understanding of the mechanisms by which AVGs may affect vision.Protocol registration The accepted stage 1 protocol for this study can be found on the Open Science Framework at https://osf.io/zdv9c/?view_only=5b3b0c161dad448d9d1d8b14ce91ab11.The stage 1 protocol for this Registered Report was accepted in principle on 01/12/22. The protocol, as accepted by the journal, can be found at: https://doi.org/10.17605/OSF.IO/ZDV9C