Video Modeling Research Articles

Alternative Approaches for the Management of Autism: A Narrative Review

Abstract: Autism, a neurodevelopment disorder that was regarded as insignificant in the past is thereby now recognized as a major problem with an increasing prevalence over the past 50 years affecting 1 out of every 160 children worldwide. Recent accumulating evidence indicates that autism is a consequence of the fusion of environmental, genetic, and epigenetic components. Due to the lack of effective pharmacotherapy, alternative approaches are being explored for their beneficial effect on autistic symptoms. A literature review was performed identifying previously published clinical studies that were set up as an alternative therapy for alleviating the symptoms of autism. The data were collected from PubMed and Google Scholar databases. A total of 13 kinds of interventions including video modelling, play therapy, music therapy, yoga, social skills training, sensory integration (SIT), scalp acupuncture, medical clowning, animal-assisted activity, theatre-based intervention, Tai Chu Chuan training, novel mattress technology, and magnetic resonance imaging were found to be affecting the symptoms associated with autism. From sufficient clinical evidence, it was estimated that alternative approaches such as music therapy and play therapy have the most beneficial effect in mitigating the symptoms to an extent.

The scoping review of systematic instruction literature for individuals with disabilities: trends in Türkiye from 1983 to 2022

ABSTRACT This study used a scoping review to examine the systematic instruction studies for individuals with disabilities published in the last four decades (1983–2022) in Türkiye. We included 332 single-case and 61 group experimental studies. We collected inter-rater reliability data for 30% of the studies and determined that the mean of inter-rater coefficients was 99.2%. The findings indicate that the studies have been mainly self-funded and performed by one or two special education researchers. Studies conducted with single-case studies were more prevalent than group experimental studies. Male participants were more than females, and more school-age children than infants and adults. Participants with intellectual disabilities and autism were the most frequently involved, and school-related academic and cognitive skills were the most commonly targeted. The most frequently used interventions were response prompting strategies, strategy instruction, video modelling and prompting, and direct instruction. Finally, we discussed the findings and made recommendations for practice and future research.

Effectiveness of video modeling in teaching earthquake and postearthquake evacuation safety skills for children with autism.

The purpose of the present study was to investigate the effectiveness of video modeling to teach safety skills during earthquakes and postearthquake evacuation to children with autism. Three male children with autism, aged 9-10 years, participated in the study. The results indicate that video modeling was effective at promoting the acquisition of "drop, cover, and hold on" and evacuation skills for all three students. Furthermore, the skills generalized to a new setting for all three participants and maintained up to 4 weeks after video modeling for the two participants for whom maintenance was evaluated. Social-validity data were also collected from participants, their parents, and a teacher, and the findings were positive overall. Implications for instruction and future research are discussed based on the results of the study.

Unsupervised corneal contour extraction algorithm with shared model for dynamic deformation videos: improving accuracy and noise resistance

BackgroundIn this study, an automatic corneal contour extraction algorithm with a shared model is developed to extract contours from dynamic corneal videos containing noise, which improves the accuracy of corneal biomechanical evaluation and clinical diagnoses. The algorithm does not require manual labeling and completes the unsupervised semantic segmentation of each frame in corneal dynamic deformation videos based on a fully convolutional deep-learning network using corneal geometry and texture information.ResultsWe included 1027 corneal videos at Tianjin Eye Hospital (Nankai University Affiliated Eye Hospital) from May 2020 to November 2021. The videos were obtained by the ultra-high-speed Scheimpflug camera, and then we used the shared model mechanism to accelerate the segmentation of corneal regions in videos, effectively resist noise, determine corneal regions based on shape factors, and finally achieve automatic and accurate extraction of corneal region contours. The Intersection over Union (IoU) of the extracted and real corneal contours using this algorithm reached 95%, and the average overlap error was 0.05, implying that the extracted corneal contour overlapped almost completely with the real contour.ConclusionsCompared to other algorithms, the method introduced in this study does not require manual annotation of corneal contour data in advance and can still extract accurate corneal contours from noisy corneal videos with good repeatability.

Evaluating Social Validity to Inform Intervention Development: Qualitative Analysis of Caregiver Interviews.

Evaluating social validity of interventions is paramount to the applied dimension of applied behavior analysis, but in research contexts, social validity is frequently assessed only after an intervention has concluded. The present study sought to evaluate the social validity of a proposed intervention prior to intervention development through qualitative analysis of interviews with stakeholders. We interviewed ten caregivers of children with autism about their experiences and challenges engaging in play with their children. We also solicited their opinions on the proposed components of the intervention, including (1) video models; (2) smart speaker prompts; and (3) feedback and coaching via video chat. Qualitative analysis of the interview transcripts revealed several domains related to caregivers' experiences, including challenges with social communication, openness to learning skills, and desires to build connections with one's child. Opinions about the proposed intervention components were largely positive, citing the convenience of using technology to access the mostly asynchronous intervention. Some participants expressed hesitation or discomfort surrounding feedback and coaching via video chat. Participants made several helpful suggestions regarding the content and features of the intervention. We discuss our findings in the context of an interactive social validation process.

A validation of an entropy-based artificial intelligence for ultrasound data in breast tumors

BackgroundThe application of artificial intelligence (AI) in the ultrasound (US) diagnosis of breast cancer (BCa) is increasingly prevalent. However, the impact of US-probe frequencies on the diagnostic efficacy of AI models has not been clearly established.ObjectivesTo explore the impact of using US-video of variable frequencies on the diagnostic efficacy of AI in breast US screening.MethodsThis study utilized different frequency US-probes (L14: frequency range: 3.0-14.0 MHz, central frequency 9 MHz, L9: frequency range: 2.5-9.0 MHz, central frequency 6.5 MHz and L13: frequency range: 3.6-13.5 MHz, central frequency 8 MHz, L7: frequency range: 3-7 MHz, central frequency 4.0 MHz, linear arrays) to collect breast-video and applied an entropy-based deep learning approach for evaluation. We analyzed the average two-dimensional image entropy (2-DIE) of these videos and the performance of AI models in processing videos from these different frequencies to assess how probe frequency affects AI diagnostic performance.ResultsThe study found that in testing set 1, L9 was higher than L14 in average 2-DIE; in testing set 2, L13 was higher in average 2-DIE than L7. The diagnostic efficacy of US-data, utilized in AI model analysis, varied across different frequencies (AUC: L9 > L14: 0.849 vs. 0.784; L13 > L7: 0.920 vs. 0.887).ConclusionThis study indicate that US-data acquired using probes with varying frequencies exhibit diverse average 2-DIE values, and datasets characterized by higher average 2-DIE demonstrate enhanced diagnostic outcomes in AI-driven BCa diagnosis. Unlike other studies, our research emphasizes the importance of US-probe frequency selection on AI model diagnostic performance, rather than focusing solely on the AI algorithms themselves. These insights offer a new perspective for early BCa screening and diagnosis and are of significant for future choices of US equipment and optimization of AI algorithms.

Effects of Visualization Format and Time of Day on Immediate Recall of Tactical Behaviors

This study examined the effect of time of day on immediate recall of motor skills (i.e., tactical behaviors in basketball) from different external visualizations. First-year students from a public university in sports science (novice practitioners, 18.96 ± 0.57 years) were quasi-randomly assigned to three experimental conditions: video modeling by experts, a sequential-with-tracing presentation of pictures, or a sequential-without-tracing presentation of pictures. Morning and late afternoon sessions were conducted involving study phases and immediate-recall tests (i.e., comprehension and game performance tests). Oral temperature and mood states were also measured at both times of day. The results revealed that participants exhibited better recall performances in the morning, irrespective of the visualization format used. At both time of day, tactical behaviors were better recalled from video modeling rather than the two sequential presentations of pictures. In addition, providing the learner with a permanent visual trace of the previous states improves the immediate recall of tactical skills from a sequential presentation of pictures, at both time of day. Furthermore, morning sessions resulted in lower oral temperature, lower negative mood, and higher positive mood, compared with afternoon sessions. Implications for using external visualizations aimed at the acquisition of motor skills, particularly tactical behaviors, are discussed.

The Effects of Using Video-Based Instruction in Solving Fraction Computations of Students with Autism Spectrum Disorder

The aim of this research was to assess whether using video modeling (VM), concrete manipulatives, a self-monitoring checklist, and practice for comprehension check impacted the extent to which five primary school students with Autism Spectrum Disorder (ASD) could accurately solve problems involving fractions. The sample of the study was purely comprised of five students owing to the challenges associated with eliciting approval to extend the study to a larger sample. A single-case multiple probe between participants experimental approach in its quasi-experimental design was employed to evaluate whether a significant association could be identified between these variables. The results revealed that from baseline to intervention, all five students solved simple proper fraction problems with greater accuracy and four were able to apply this ability to solve problems involving whole proper fractions. Given these results, the researchers recommend that to cater for the disparate learning needs of students with ASD across a range of settings, teachers should consider implementing interventions comprising VM and concrete manipulatives in conjunction with certain behavioural techniques. Owing to the challenges associated with eliciting approval to extend the study to a larger sample. Keywords: primary school, autism, mathematics, video‑based instruction, concrete manipulatives, self-monitoring strategy

Development of a Social Communication Skills Intervention Using Video Modeling and Spherical Video-Based Virtual Reality for High Functioning Autism Spectrum Disorder Youth: A Preliminary Study

Development of a Social Communication Skills Intervention Using Video Modeling and Spherical Video-Based Virtual Reality for High Functioning Autism Spectrum Disorder Youth: A Preliminary Study

Construction of an intelligent recommendation model for microblog short videos based on ABC-BPNN

Construction of an intelligent recommendation model for microblog short videos based on ABC-BPNN

Unified Audio-Visual Saliency Model for Omnidirectional Videos With Spatial Audio

Unified Audio-Visual Saliency Model for Omnidirectional Videos With Spatial Audio

Learning Temporal Distribution and Spatial Correlation Toward Universal Moving Object Segmentation.

The goal of moving object segmentation is separating moving objects from stationary backgrounds in videos. One major challenge in this problem is how to develop a universal model for videos from various natural scenes since previous methods are often effective only in specific scenes. In this paper, we propose a method called Learning Temporal Distribution and Spatial Correlation (LTS) that has the potential to be a general solution for universal moving object segmentation. In the proposed approach, the distribution from temporal pixels is first learned by our Defect Iterative Distribution Learning (DIDL) network for a scene-independent segmentation. Notably, the DIDL network incorporates the use of an improved product distribution layer that we have newly derived. Then, the Stochastic Bayesian Refinement (SBR) Network, which learns the spatial correlation, is proposed to improve the binary mask generated by the DIDL network. Benefiting from the scene independence of the temporal distribution and the accuracy improvement resulting from the spatial correlation, the proposed approach performs well for almost all videos from diverse and complex natural scenes with fixed parameters. Comprehensive experiments on standard datasets including LASIESTA, CDNet2014, BMC, SBMI2015 and 128 real world videos demonstrate the superiority of proposed approach compared to state-of-the-art methods with or without the use of deep learning networks. To the best of our knowledge, this work has high potential to be a general solution for moving object segmentation in real world environments. The code and real-world videos can be found on GitHub https://github.com/guanfangdong/LTS-UniverisalMOS.

MAR: Masked Autoencoders for Efficient Action Recognition

Standard approaches for video action recognition usually operate on full input videos, which is inefficient due to the widespread spatio-temporal redundancy in videos. The recent progress in masked video modelling, specifically VideoMAE, has shown the ability of vanilla Vision Transformers (ViT) to complement spatio-temporal contexts using limited visual content. Inspired by this, we propose Masked Action Recognition (MAR), which reduces redundant computation by discarding a proportion of patches and operating only on a portion of the videos. MAR includes two essential components: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cell running masking</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">bridging classifier</i> . Specifically, to enable the ViT to perceive the details beyond the visible patches, cell running masking is used to preserve the spatio-temporal correlations in videos. This ensures that the patches at the same spatial location can be observed in turn for easy reconstructions. Additionally, we notice that, although the partially observed features can reconstruct semantically explicit invisible patches, they fail to achieve accurate classification. To address this issue, we propose a bridging classifier that can help fill the semantic gap between the ViT encoded features used for reconstruction and the specialized features used for classification. Our proposed MAR can reduce the computational cost of ViT by 53%. Extensive experiments have demonstrated that MAR consistently outperforms existing ViT models by a notable margin. Notably, we found that a ViT-Large model fine-tuned by MAR achieves comparable performance to a ViT-Huge model fine-tuned by standard training methods on both Kinetics-400 and Something-Something v2 datasets. Moreover, the computation overhead of our ViT-Large model is only 14.5% of that of the ViT-Huge model. Codes have been made available <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/alibaba-mmai-research/Masked-Action-Recognition</uri> .

Violence Detection in Video Models Implementation Using Pre-trained VGG19 Combined With Manual Logic, LSTM Layers and Bi-LSTM layers

Violence Detection in Video Models Implementation Using Pre-trained VGG19 Combined With Manual Logic, LSTM Layers and Bi-LSTM layers

An Analysis on English Teachers’ Effective Classroom Discourse and Its Interactive Model Innovation with the Assistance of Artificial Intelligence

Abstract The rapid evolution of technology catalyzes innovation in English teaching methodologies, rendering traditional approaches—predominantly reliant on singular language modalities—insufficient for modern educational demands. This paper introduces a multimodal English teaching model anchored in multimodal discourse analysis and interaction theory to address these evolving needs. Utilizing a dual threshold extraction algorithm for chunked cumulative frame difference, the model effectively identifies semantic key frames during multimodal English instruction. Additionally, it incorporates a composite convolutional neural network that merges spatio-temporal features to delineate the dynamics of the teaching videos, further enhanced by the LK optical flow method. The integration of a pre-interactive LSTM decoder facilitates the fusion of video and textual features, culminating in the construction of an annotated English teaching video model. This model was applied to analyze the classroom discourse of high school sophomores’ English teachers in X city. Analysis revealed that the duration of classroom discourse varied between 14 to 19 minutes per session, with the introductory segment alone accounting for 307.54 seconds—12.81% of the total lesson duration—of purely linguistic content. Furthermore, the average number of questions posed by teachers per lesson was 73.17, indicating a high reliance on verifying discourse strategies, which constituted 92.22% of the discourse. This technological approach to analyzing classroom discourse provides novel insights and valuable references for refining English teaching strategies, demonstrating the effectiveness of integrating advanced computational techniques in educational settings.

Influence of video modeling in sports performance: A Bibliometric analysis

Influence of video modeling in sports performance: A Bibliometric analysis

THESE GIRLS (STRIP) FOR THE CLOUT: EXPLORING ASPIRATIONAL, EMOTIONAL AND EROTIC LABOR OF BLACK WOMEN HIP-HOP ARTISTS ON ONLYFANS

In the digital age, OnlyFans is suggested to be a new form of sexual empowerment, financial autonomy and social agency for Black women working as strippers, backup dancers and video models, particularly those ancillaries to the rap music industry. Through interviews and participant observation, I examine the everyday labor of Black women who work as sexually explicit content creators on OnlyFans while also building a public persona as artists in Hip-Hop culture. Findings suggested that despite financial opportunities, respondents felt ambivalent by the monetization opportunities afforded by this digital space. Even so, respondents enjoyed the affordances of promoting their OnlyFans content on social media to gain digital clout - a form of Hip-Hop influenced cultural capital that follows the logic of likes, followers, and re-shares of one’s social media content. Ultimately, this study introduces insights on the evolution of Hip-Hop culture’s relationship with sex work, digital Black feminism and the attention economy.

Training in medical communication competence through video-based e-learning: How effective are video modeling and video reflection?

ObjectiveThe present study investigated the efficacy of the didactic approaches of video modeling (VM, best-practice examples), video reflection (VR, problem-based approach), and the combination of both (VMR) in fostering medical communication competence in a video-based digital learning environment. MethodsN = 126 third-year medical students who participated in the pre-post study were assigned to either the intervention groups (VM, VR, and VMR) or the wait-list control group. The efficacy of the three approaches was assessed by means of a situational judgment test (SJT) of medical communication competence. To investigate the differences between the wait-list control and the intervention groups (H1), between the single-mode and combined conditions (H2), and between VM and VR (H3), we applied planned contrast analyses. ResultsThe planned contrasts showed that the VR condition significantly improved learning outcomes in comparison to the VM condition (H3). The decreased mean scores of the VM condition offset the increased mean scores of VR, and thus no significant differences could be found in H1 and H2. ConclusionsOur study provides promising evidence that VR fosters medical communication competence more effectively than VM. Practical implicationsMedical students’ learning in video-based digital environments can be facilitated by the use of interactive VR.

2BiVQA: Double Bi-LSTM-based Video Quality Assessment of UGC Videos

Recently, with the growing popularity of mobile devices as well as video sharing platforms (e.g., YouTube, Facebook, TikTok, and Twitch), User-Generated Content (UGC) videos have become increasingly common and now account for a large portion of multimedia traffic on the internet. Unlike professionally generated videos produced by filmmakers and videographers, typically, UGC videos contain multiple authentic distortions, generally introduced during capture and processing by naive users. Quality prediction of UGC videos is of paramount importance to optimize and monitor their processing in hosting platforms, such as their coding, transcoding, and streaming. However, blind quality prediction of UGC is quite challenging, because the degradations of UGC videos are unknown and very diverse, in addition to the unavailability of pristine reference. Therefore, in this article, we propose an accurate and efficient Blind Video Quality Assessment (BVQA) model for UGC videos, which we name 2BiVQA for double Bi-LSTM Video Quality Assessment. 2BiVQA metric consists of three main blocks, including a pre-trained Convolutional Neural Network to extract discriminative features from image patches, which are then fed into two Recurrent Neural Networks for spatial and temporal pooling. Specifically, we use two Bi-directional Long Short-term Memory networks, the first is used to capture short-range dependencies between image patches, while the second allows capturing long-range dependencies between frames to account for the temporal memory effect. Experimental results on recent large-scale UGC VQA datasets show that 2BiVQA achieves high performance at lower computational cost than most state-of-the-art VQA models. The source code of our 2BiVQA metric is made publicly available at https://github.com/atelili/2BiVQA .

Optimal coding unit decision for early termination in high efficiency video coding using enhanced whale optimization algorithm

Video compression is an emerging research topic in the field of block based video encoders. Due to the growth of video coding technologies, high efficiency video coding (HEVC) delivers superior coding performance. With the increased encoding complexity, the HEVC enhances the rate-distortion (RD) performance. In the video compression, the out-sized coding units (CUs) have higher encoding complexity. Therefore, the computational encoding cost and complexity remain vital concerns, which need to be considered as an optimization task. In this manuscript, an enhanced whale optimization algorithm (EWOA) is implemented to reduce the computational time and complexity of the HEVC. In the EWOA, a cosine function is incorporated with the controlling parameter A and two correlation factors are included in the WOA for controlling the position of whales and regulating the movement of search mechanism during the optimization and search processes. The bit streams in the Luma-coding tree block are selected using EWOA that defines the CU neighbors and is used in the HEVC. The results indicate that the EWOA achieves best bit rate (BR), time saving, and peak signal to noise ratio (PSNR). The EWOA showed 0.006-0.012 dB higher PSNR than the existing models in the real-time videos.