Active Video Research Articles

How do parents experience patching or dichoptic action video gaming as amblyopia treatment? A qualitative study exploring treatment preferences and information needs to facilitate decision‐making

To explore parents' experiences, preferences and information needs when either patching treatment or dichoptic action video gaming is used as an amblyopia treatment for their child. A qualitative study was carried out on parents whose newly diagnosed amblyopic children participated in a randomised controlled trial (RCT) comparing the effects of dichoptic action video gaming versus patching. A purposive heterogenic sample was selected for an additional interview after the study period. Semi-structured interviews were conducted with one or both parents and transcribed verbatim, and a thematic analysis was performed. Ten families agreed to participate: seven in the patching group and three in the gaming group. Two themes emerged from the data exploring experiences with treatment: (1) factors influencing compliance and (2) burden with treatment. Parents reported creating a routine which improved compliance with patching, as opposed to gaming where parents felt less need to conduct the treatment themselves as it was performed in the outpatient clinic. In both groups, parents experienced an information hiatus regarding the role of refractive error. In deciding the type of treatment to be used, parents preferred to deliberate the choice with the healthcare professional and discuss considerations resulting in shared decisions. The emerging themes were (1) effect and efficiency of treatment, (2) organisational aspects of treatments and (3) their child's traits. This study provides insight into the experiences of parents whose children underwent different types of amblyopia therapy. Both treatments have their own advantages and disadvantages. For parents, the effectiveness and efficiency of treatment were the most important aspects when deciding the method of management. Parents wish to come to a well-informed, shared decision regarding the type of amblyopia treatment.

Performance Art Video Action Management Oriented to 6G Wireless Transmission Technology

With the development of 5G communication networks, the development prospects, capability requirements and key technologies of the next-generation communication system 6G have become new hotspots. This article expands the coverage of the communication system through 6G, realizes the wireless transmission technology, builds the ideal of an intelligent mobile society everywhere, and analyzes the development trend of 6G technology, the challenges it faces, and the possible wireless transmission technology. Wireless transmission technology is widely used in various fields of production and life. Its various technical requirements and terminal energy limitations restrict the application and development of communications. This article focuses on the high-efficiency optimization scheme that combines 6G wireless transmission technology to improve the utilization efficiency of network resources. In addition, this thesis also discusses video action management in public performance art. Based on public performance art, the research on video action recognition can be summarized into three levels from simple to complex according to the content of the action, namely mobile vision, action vision and action vision. Video action vision is currently being studied. In the recognition process, most of the action frame information in the video is repetitive or has a low correlation with action recognition, which not only increases the complexity of calculation, but also affects the accuracy of action recognition. In the process of feature selection and understanding, the main methods include characterization fusion and research based on gesture features. Based on the introduction of 6G wireless transmission technology, this article introduces the technological development of 6G network, which promotes the rapid development of public performance art video action management.

PD30-03 IMPORTANCE OF COGNITIVE LOAD FOR AUTOMATED ERROR DETECTION IN ROBOT-ASSISTED SURGERY EDUCATION

You have accessJournal of UrologyCME1 Apr 2023PD30-03 IMPORTANCE OF COGNITIVE LOAD FOR AUTOMATED ERROR DETECTION IN ROBOT-ASSISTED SURGERY EDUCATION Rafal Kocielnik, Jasper A. Laca, Elyssa Y. Wong, Timothy N. Chu, Sidney I. Roberts, Sandra Marshall, Anima Anandkumar, and Andrew J. Hung Rafal KocielnikRafal Kocielnik More articles by this author , Jasper A. LacaJasper A. Laca More articles by this author , Elyssa Y. WongElyssa Y. Wong More articles by this author , Timothy N. ChuTimothy N. Chu More articles by this author , Sidney I. RobertsSidney I. Roberts More articles by this author , Sandra MarshallSandra Marshall More articles by this author , Anima AnandkumarAnima Anandkumar More articles by this author , and Andrew J. HungAndrew J. Hung More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003316.03AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Cognitive Load (CL) can affect surgeon performance and the ability of training surgeons to receive feedback. We investigate the value of CL for detecting surgical errors in robot-assisted surgery (RAS) with a machine learning (ML)-based model. METHODS: We use 2 datasets (DS1, DS2) where 24 and 44 surgeons, respectively, performed a simulated dry-lab tissue dissection task on a live daVinci Xi surgical robot. The data contains video and per-second Index of Cognitive Activity (ICA), derived from pupillary change tracked via Tobii Eyetrackers. DS1 includes surgeons with low, medium, and high experience (by hours of RAS) as well as annotated tissue Tear (n=70) and Puncture (n=62) errors. DS2 contains data from low experience surgeons only and annotations for Tears (n=445) and Punctures (n=527). We extract 5 sec of video and varying history of ICA (from 5 to 60 sec) before and around human-labeled errors (positive label). We randomly sample the remaining data (negative label). We train variations of ML architecture consisting of video processing (pretrained Resnet18) and/or ICA processing (LSTM). We train the model on 3 different 80/20 train-test between-participant random splits. RESULTS: When including surgeons of mixed experience levels (DS1), ICA alone (AUC=64.28) is competitive with video alone (AUC=62.59) in detecting surgical errors (Figure 1A). However, the use of ICA in combination with video improves AUC in both datasets with gains of 5.55 (DS1) and 3.24 (DS2). History of ICA up to 20-30 seconds seems beneficial for error detection, after which point there is no further gain (Figure 1B). This is likely attributed to gradual build-up in CL leading to an error, and low-frequency of ICA measurements (1/sec), which may hinder extracting useful information from short time windows. The challenge of extracting meaningful information seems supported by Figure 1C, where providing processed ICA is beneficial (AUC=62.95) on top of raw ICA measurements (AUC=58.88). CONCLUSIONS: A surgeon’s CL in the context of surgical errors in RAS education is important. We show how CL is particularly valuable when a dataset includes mixed-experience surgeons. We also show the importance of ICA history length and pre-processing. Further work will explore better methods of extracting valuable features from CL data and its importance in surgery. Source of Funding: This material is based upon work supported by the National Science Foundation under Grant # 2030859 to the Computing Research Association for the CIFellows Project. Additionally, research reported in this publication was supported by the National Cancer Institute of the National Institutes of Health under Award Number R01CA273031. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e831 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Rafal Kocielnik More articles by this author Jasper A. Laca More articles by this author Elyssa Y. Wong More articles by this author Timothy N. Chu More articles by this author Sidney I. Roberts More articles by this author Sandra Marshall More articles by this author Anima Anandkumar More articles by this author Andrew J. Hung More articles by this author Expand All Advertisement PDF downloadLoading ...

Biomechanical Risk Factors of the Upper Limbs' Musculoskeletal Disorders among Carpet Weavers in Tunisia: Semi-Quantitative Ergonomic Assessment.

Musculoskeletal disorders are one of the most common occupational health problems and one of the leading causes of temporary disability. This study aimed to assess the biomechanical constraints of upper limb musculoskeletal disorders associated with Tunisian weavers' tasks. An ergonomic approach was adopted with a representative sample of Tunisian weavers. First, the activity was observed mainly for identifying tasks and sub-tasks. Then, the biomechanical constraints were assessed based on the Borg scale and the software analyses and encoding of the 2,000 images extracted from the activity video recordings. These analyses were done with the ERGOROM software. Four main tasks were identified (warping of the loom, weaving itself, beating up, and finishing). As for the subtasks, the six most important were thread coiling, shedding and picking, beating up the weft, knotting, cutting, and shearing. Semi-quantitative analysis revealed that weavers spent most of their working time in the constrained neck and upper limb postures. Shoulders were in flexion/abduction during 68.6% of the activity and pinch grip was spread over 83.3% of the working time. Furthermore, elbows and wrists were highly concerned by elevated gestural variability scores. The estimated deployed strength was "medium" to "strong" in 50% to nearly 80% of cases. According to the results, in carpet weavers, exposure to biomechanical constraints at risk of musculoskeletal disorders was high for the various joints and parts of the upper limbs. It is, therefore, necessary to carry out interventional studies for the development of ergonomic hand tools and workstations adapted to the traditional weaver activity.

Differential influence of first- vs. third-person visual perspectives on segmentation and memory of complex dynamic events

Until now, most studies investigating the relationship between event segmentation and memory have used videos filmed from a third-person perspective, although people experience their lives from a first-person perspective. The present study aimed to determine whether visual perspective impacts events segmentation and further recall. Fifty-seven participants were recruited and assigned to either first- (1PP) or third-person perspective (3PP) condition, before segmenting videos of daily life activities. Our results showed that the although the number of event boundaries was higher in the 3PP condition than in the 1PP, no differences were observed for event segmentation qualitative abilities and organization. Memory of temporal order was better for events encoded in the 3PP than in the 1PP, while memory content was similar in both conditions. Higher event segmentation rates were correlated with a better recall of small actions and temporal order.

Analysis on the Type of and Interest in Home Training Video Contents Using the YouTube Platform

PURPOSE The purpose of this study is to analyze the type of and interest in home training video contents using the YouTube platform. METHODS Web crawling was performed using Python and a total of 3,937 sets ofvideo information (title, content, number of views, upload date) were obtained, 3,155 of which were finally selected for the study material. Overlapping and unrelated content were excluded. The data of text underwent 3 stages of preprocessing, the TF and TF-IDF of the keywords were calculated to identify the main keywords, and the LDA algorithm was applied in the topic modeling to successfully identify the types. In order to understand the level of interest by type, the number of views was subdivided into the percentage of the assigned type. RESULTS First, the types of home training videos were classified into bare whole body exercise for aerobic and muscular power strengthening, Pilates exercise for core and upper body strengthening, upper body exercise using tools, lower body line exercise, posture correction and upper body stretching exercise for pain relief, hip-up exercise, dance and tabata exercise for diet, diet and lower body correction stretching exercise for diet, and bare body exercise for core and lower body strengthening. Second, it was found that the proportion and interest were high in the contents of bare whole body exercise for aerobic and muscular power strengthening, dance and tabata exercise for diet, diet and lower body correction stretching exercise for diet. CONCLUSIONS The findings of this study may provide baseline data about the development of the active online home training videos in the market.

Internet-Based Video Program to Promote Physical Activity, Health, and Well-Being of Brazilian Older Adults during the COVID-19 Pandemic

In 2020 and 2021, the SARS-CoV-2 coronavirus spread rapidly across the world, causing the COVID-19 pandemic with millions of deaths. One of the measures to protect life was confinement, which negatively affected physical and mental health, especially of the older population. The aim of this study is to present and evaluate the methodological procedures of a telehealth and eHealth program “U3A in Motion”, which was composed of videos of physical exercises and activities to promote the mental health and well-being of the older Brazilian population during the COVID-19 pandemic. The procedures included the planning, editing, and dissemination of videos through WhatsApp, and also on the YouTube platform, Instagram, and on a website. A total of 82 videos were created. The action reached 350 older adults from the local community in the northeast of Brazil, as well as being accessed by approximately 3000 other older adults from institutions in the southern region of Brazil. Based on the evaluation of activities through telephone interviews, it was found that older adults participating in the “U3A in Motion” program during confinement were highly motivated to access exercise activities, mainly via mobile phones, and reported a positive effect on physical and mental health.

AMIR

Activity recognition using video data is widely adopted for elder care, monitoring for safety and security, and home automation. Unfortunately, using video data as the basis for activity recognition can be brittle, since models trained on video are often not robust to certain environmental changes, such as camera angle and lighting changes. There has been a proliferation of network-connected devices in home environments. Interactions with these smart devices are associated with network activity, making network data a potential source for recognizing these device interactions. This paper advocates for the synthesis of video and network data for robust interaction recognition in connected environments. We consider machine learning-based approaches for activity recognition, where each labeled activity is associated with both a video capture and an accompanying network traffic trace. We develop a simple but effective framework AMIR (Active Multimodal Interaction Recognition)1 that trains independent models for video and network activity recognition respectively, and subsequently combines the predictions from these models using a meta-learning framework. Whether in lab or at home, this approach reduces the amount of "paired" demonstrations needed to perform accurate activity recognition, where both network and video data are collected simultaneously. Specifically, the method we have developed requires up to 70.83% fewer samples to achieve 85% F1 score than random data collection, and improves accuracy by 17.76% given the same number of samples.

Improved attentional abilities after playing five weeks of active video games in children with and without developmental coordination disorder

Background Besides motor coordination problems, attentional impairments are reported in children with developmental coordination disorder (DCD), but the connection or trainability is still unclear. Aim To test changes on attentional abilities after playing active video games (AVG) in children with DCD and their peers (TD), to evaluate near transfer and the relationship between omissions in attentional and motor tests. Methods Seventy children (35 DCD; 35 TD), 7–12 years old, were assessed on three types of attention: distractibility (DIS); divided-attention (DA); sustained-attention (SA) and on the Wii Fit test pre- and post-training. Results A significant decrease of errors in attentional tasks was found after training, independent of group (TD/DCD) and console (Wii Fit/Xbox) with medium-strong effect sizes (DIS η2 p =.42; DA η2 p =.51; SA η2 p =.41). The groups responded similarly to the training but the DCD children scored poorer on the DA. A positive transfer-effect to the non-trained Wii Fit test was found in accuracy (missed gates), while speed proved console-specific. A medium/strong relation was found between omissions in attentional tasks and the missed gates (Wii Fit test). Conclusion More accurate responses on attentional tasks were found after AVG-training in both groups. A clear relationship between attentional abilities and motor performance was found.

See, move and hear: a local-to-global multi-modal interaction network for video action recognition

See, move and hear: a local-to-global multi-modal interaction network for video action recognition

Worksheets and Joyful Teaching Strategies in Teaching English to Students of English Village of Parit Baru

English lessons are not compulsory in public elementary schools. It makes English a challenge for students in Indonesia's foreign language communication from an early age. This study aimed to find student worksheets and fun learning strategies, including singing and mentoring activities, to be implemented in teaching English to students. This research includes case study research. This study used a sampling technique to select five fifth-grade students who participated in this program. Data collection was carried out using participant observation techniques, and the documents included were student worksheets, photos, and activity videos. Data analysis techniques using thematic analysis techniques. The study results show that student worksheets and fun learning strategies can help students in English Village learn English through all teaching stages. It was concluded that alternative learning in the form of English Village using student worksheets and fun learning strategies had been proven to help students learn English by providing brief material that is clear and easy to understand.

Aeriform in-action: A novel dataset for human action recognition in aerial videos

Human actions being diverse in nature cannot be generalized, thus making it quite difficult to train a machine to recognize such diversified actions. This challenge is further compounded by the lack of availability of datasets for aerial surveillance, as collecting and annotating a large dataset is a formidable task. This paper aims to solve the problem of data scarcity by introducing a new dataset, Aeriform in-action for recognizing human actions from aerial videos. The proposed dataset consists of 32 high-resolution videos containing 13 action classes with 55,477 frames (without augmentation) and almost 400,000 annotations. It includes complex and aggressive actions such as kicking and punching, as well as drone signaling actions like waving and handshaking. The dataset also includes human-object interactions like carrying and reading. In addition to the dataset, this paper also presents a two-step deep learning framework for recognizing human actions based on the integration of human detection and action recognition module. The action recognition module adopts a modified version of the ResNeXt101 architecture (M-ResNext101) to recognize human actions in aerial videos. The performance of the proposed M-ResNext101 model is compared with 13 other deep learning models, and it outperforms all of them with an accuracy of 76.44% on the test data. The proposed dataset for human action recognition in aerial videos is available on https://surbhi-31.github.io/Aeriform-in-action/.

Supplemental Material for Effects of action video game play on cognitive skills: A meta-analysis.

The possibility that playing action video games is associated with enhancements in certain aspects of cognitive function has attracted significant interest from researchers in education, psychology, and neuroscience. Previous meta-analyses indicated an overall positive relationship between action video game play and cognitive skills. However, follow-up to this previous work is warranted, not only because the amount of data has grown significantly since previous meta-analyses were conducted, but also because previous work left several issues unresolved (e.g., certain meta-analytic procedures). We conducted a literature search using predefined keywords and inclusion criteria to identify studies that examined the relationship between action video game play and cognitive skills. Data from (a) 105 cross-sectional studies (221 effect sizes) and (b) 28 intervention studies with an active control group (91 effect sizes) were analyzed separately via meta-analytic models for dependent effect sizes with robust variance estimates for correlated and hierarchical effects (CHE) and small-sample corrections. Consistent with our hypotheses, action video game players outperformed nonvideo game players in the cross-sectional meta-analysis (large effect, g = 0.64, 95% CI [0.53, 0.74]). Action video game play was causally related to improvements in cognitive skills in the intervention meta-analysis (small effect, g = 0.30, 95% CI [0.11, 0.50]). Publication bias was detected in the cross-sectional data set, with sensitivity analysis showing high heterogeneous estimates of the average unbiased effect. Publication bias was not detected in the intervention data set, but sensitivity analyses also point to heterogeneity. No significant moderators were found for either data set; however, this may be limited by small sample sizes.

Effects of action video game play on cognitive skills: A meta-analysis.

The possibility that playing action video games is associated with enhancements in certain aspects of cognitive function has attracted significant interest from researchers in education, psychology, and neuroscience. Previous meta-analyses indicated an overall positive relationship between action video game play and cognitive skills. However, follow-up to this previous work is warranted, not only because the amount of data has grown significantly since previous meta-analyses were conducted, but also because previous work left several issues unresolved (e.g., certain meta-analytic procedures). We conducted a literature search using predefined keywords and inclusion criteria to identify studies that examined the relationship between action video game play and cognitive skills. Data from (a) 105 cross-sectional studies (221 effect sizes) and (b) 28 intervention studies with an active control group (91 effect sizes) were analyzed separately via meta-analytic models for dependent effect sizes with robust variance estimates for correlated and hierarchical effects (CHE) and small-sample corrections. Consistent with our hypotheses, action video game players outperformed nonvideo game players in the cross-sectional meta-analysis (large effect, g = 0.64, 95% CI [0.53, 0.74]). Action video game play was causally related to improvements in cognitive skills in the intervention meta-analysis (small effect, g = 0.30, 95% CI [0.11, 0.50]). Publication bias was detected in the cross-sectional data set, with sensitivity analysis showing high heterogeneous estimates of the average unbiased effect. Publication bias was not detected in the intervention data set, but sensitivity analyses also point to heterogeneity. No significant moderators were found for either data set; however, this may be limited by small sample sizes.

Relational Action Bank with Semantic–Visual Attention for Few-Shot Action Recognition

Recently, few-shot learning has attracted significant attention in the field of video action recognition, owing to its data-efficient learning paradigm. Despite the encouraging progress, identifying ways to further improve the few-shot learning performance by exploring additional or auxiliary information for video action recognition remains an ongoing challenge. To address this problem, in this paper we make the first attempt to propose a relational action bank with semantic–visual attention for few-shot action recognition. Specifically, we introduce a relational action bank as the auxiliary library to assist the network in understanding the actions in novel classes. Meanwhile, the semantic–visual attention is devised to adaptively capture the connections to the foregone actions via both semantic correlation and visual similarity. We extensively evaluate our approach via two backbone models (ResNet-50 and C3D) on HMDB and Kinetics datasets, and demonstrate that the proposed model can obtain significantly better performance compared against state-of-the-art methods. Notably, our results demonstrate an average improvement of about 6.2% when compared to the second-best method on the Kinetics dataset.

The Empathy for Pain Stimuli System (EPSS): Development and preliminary validation

We present the Empathy for Pain Stimuli System (EPSS): a large-scale database of stimuli for studying people’s empathy for pain. The EPSS comprises five sub-databases. First, the Empathy for Limb Pain Picture Database (EPSS-Limb) provides 68 painful and 68 non-painful limb pictures, exhibiting people’s limbs in painful and non-painful situations, respectively. Second, the Empathy for Face Pain Picture Database (EPSS-Face) provides 80 painful and 80 non-painful pictures of people’s faces being penetrated by a syringe or touched by a Q-tip. Third, the Empathy for Voice Pain Database (EPSS-Voice) provides 30 painful and 30 non-painful voices exhibiting either short vocal cries of pain or neutral interjections. Fourth, the Empathy for Action Pain Video Database (EPSS-Action_Video) provides 239 painful and 239 non-painful videos of whole-body actions. Finally, the Empathy for Action Pain Picture Database (EPSS-Action_Picture) provides 239 painful and 239 non-painful pictures of whole-body actions. To validate the stimuli in the EPSS, participants evaluated the stimuli using four different scales, rating pain intensity, affective valence, arousal, and dominance. The EPSS is available to download for free at https://osf.io/muyah/?view_only=33ecf6c574cc4e2bbbaee775b299c6c1.

SOR-TC: Self-attentive octave ResNet with temporal consistency for compressed video action recognition

Modeling and recognizing video activities from videos are key parts of many promising applications such as visual surveillance, human–computer interaction, and video summarization. However, current approaches mainly suffer from two issues: (a) Short-term local and global spatial features are not well represented. The spatial redundancy and dependency have not been well considered on CNN-based action recognition, which may result in a further increase in both memory and computation cost. (b) Long-term temporal consistency is not well captured. The action consistency across multiple clips has been ignored in video-level action recognition approaches. To address these two issues, we propose a Self-Attentive Octave ResNet with Temporal Consistency (SOR-TC) for compressed video action recognition to better capture the short-term and long-term features in video and improve the efficiency and effectiveness of action recognition. In addition, this paper introduces a consistency hypothesis that adjacent clips should predict similar actions. So the consistency loss function is designed to learn the correlation of clips. Finally, extensive experimental results on two benchmark datasets HMDB-51 and UCF-101 verify the effectiveness of our proposed method.

Fall-Perceived Action Recognition of Persons With Neurological Disorders Using Semantic Supervision

Frequent uncertain falls is one of the common cause of injury among elderly adults and persons suffering from the neurological disorder. It will be costlier to go through <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$24\times 7$ </tex-math></inline-formula> medical monitoring if we monitor a person suffering from the early stage of the neurological disorder. An “uncertain” action classification model can be a less costly and easily scalable. It can help to regularly monitor a person suffering from neurological declines and how frequent it relapse. In this article, we propose a video-based action recognition with fall detection architecture, FallNet, which learns the features of uncertain actions related to day-to-day activities. FallNet first incorporates semantic supervision using the per-class weight of uncertain action through class-wise weighted focal loss. It addresses both the class imbalance problem and the weak interclass separability issue. We design a joint training model to train the overall architecture efficiently in an end-to-end manner. We utilize benchmark data sets, OOPS, HMDB51, and Kinetics-600, for experimentation that has less falling action videos. Therefore, we have collected videos to create a data set, denoted by FallAction, that consists of different 15 falling action classes with an average of 100 videos per class. The proposed network gain an accuracy of 13.2% in OOPs, 2% in HMDB51, and 0.2% in Kinetics-600 data set.

Semi-Supervised Action Recognition From Temporal Augmentation Using Curriculum Learning

Semi-supervised learning for video action recognition is a very challenging research area. Existing state-of-the-art methods perform data augmentation on the temporality of actions, which are combined with the mainstream consistency-based semi-supervised learning framework FixMatch for action recognition. However, these approaches have the following limitations: (1) data augmentation based on video clips lacks coarse-grained and fine-grained representations of actions in temporal sequences, and the models have difficulty understanding synonymous representations of actions in different motion phases. (2) Pseudo labeling selection based on the constant thresholds lacks a “make-up curriculum” for difficult actions, that results in the low utilization of unlabeled data corresponding to difficult actions. To address the above shortcomings, we propose a semi-supervised action recognition via the temporal augmentation using curriculum learning (TACL) algorithm. Compared to previous works, TACL explores different representations of the same semantics of actions in temporal sequences for video and uses the idea of curriculum learning (CL) to reduce the difficulty of the model training process. First, for different action expressions with the same semantics, we designed the temporal action augmentation (TAA) for videos to obtain coarse-grained and fine-grained action expressions based on constant-velocity and hetero-velocity methods, respectively. Second, we construct a temporal signal to constrain the model such that fine-grained action expressions containing different movement phases have the same prediction results, and achieve action consistency learning (ACL) by combining the label and pseudo-label signals. Finally, we propose action curriculum pseudo labeling (ACPL), a loosely and strictly parallel dynamic threshold evaluation algorithm for selecting and labeling unlabeled data. We evaluate TACL on three standard public datasets: UCF101, HMDB51, and Kinetics. The combined experiments show that TACL significantly improves the accuracy of models trained on a small amount of labeled data and better evaluates the learning effects for different actions.

Activity Videos Effect on Four-, Five- and Six-Year-Olds' Physical Activity Level in Preschool.

Physical activity provides positive health benefits for preschool children. The aim of this study is to examine the effect of physical activity videos on the physical activity levels of children aged 4, 5 and 6 in preschool time. Two preschools served as a control group, and four served as intervention groups. The study included 110 children aged 4-6 years, all wearing accelerometers in the preschool for two weeks. In the first week, both the control group and the intervention group carried out their ordinary activities. In the second week, the four preschools in the intervention group used the activity videos, while the control group continued their ordinary activities. The main finding is that the activity videos only increased the 4 year olds' physical activity in MVPA (moderate to vigorous physical activity) from pre-test to post-test. Furthermore, the results show significantly increased CPM (counts per minute) in preschool among 4- and 6-year-old children in the interventions group from pre-test to post-test. However, the children in the control group did not have a significant change in their CPM or MVPA from pre-test to post-test. Our findings indicate that the use of activity videos may increase preschool children's activity levels at preschool, but that the videos need to be developed differently depending on the age of the children.