Test Video Research Articles

Real-Time Human Detection and Counting System Using Deep Learning Computer Vision Techniques

Targeting the current Covid 19 pandemic situation, this paper identifies the need of crowd management. Thus, it proposes an effective and efficient real-time human detection and counting solution specifically for shopping malls by producing a system with graphical user interface and management functionalities. Besides, it comprehensively reviews and compares the existing techniques and similar systems to select the ideal solution for this scenario. Specifically, advanced deep learning computer vision techniques are decided by using YOLOv3 for detecting and classifying the human objects with DeepSORT tracking algorithm to track each detected human object and perform counting using intrusion line judgment. Additionally, it converts the pretrained YOLOv3 into TensorFlow format for better and faster real-time computation using graphical processing unit instead of using central processing unit as the traditional target machine. The experimental results have proven this implementation combination to be 91.07% accurate and real-time capable with testing videos from the internet to simulate the shopping mall entrance scenario.

Video Validation of Tri-Axial Accelerometer for Monitoring Zoo-Housed Tamandua tetradactyla Activity Patterns in Response to Changes in Husbandry Conditions.

Simple SummaryIn recent years, the use of technologies to remotely monitor animal behaviour has increased. However, when they are used for the first time in a new species, validation is needed. Therefore, a tri-axial accelerometer was used to monitor lesser anteater (Tamandua tetradactyla) behaviour. First, the influence of using a vest on the animals’ behaviour was evaluated. Second, correlations between video recordings and accelerometer data were made, allowing the researchers to obtain summary measures for each behaviour and a threshold to discriminate activity/inactivity events. Sensitivity and precision variables revealed the robustness of accelerometer monitoring. Third, animals responded to a reduction in enclosure complexity by increasing their activity. The relevance of the accelerometer was determined comparing data (activity level and activity cycle) with video recordings. The results indicate that an accelerometer attached to a vest is a reliable technology for monitoring the activity pattern of T. tetradactyla under semi-controlled environmental conditions.Accelerometers are a technology that is increasingly used in the evaluation of animal behaviour. A tri-axial accelerometer attached to a vest was used on Tamandua tetradactyla individuals (n = 10) at Biodiversity Park. First, the influence of using a vest on the animals’ behaviour was evaluated (ABA-type: A1 and A2, without a vest; B, with a vest; each stage lasted 24 h), and no changes were detected. Second, their behaviour was monitored using videos and the accelerometer simultaneously (experimental room, 20 min). The observed behaviours were correlated with the accelerometer data, and summary measures (X, Y and Z axes) were obtained. Additionally, the overall dynamic body acceleration was calculated, determining a threshold to discriminate activity/inactivity events (variance = 0.0055). Then, based on a 24 h complementary test (video sampling every 5 min), the sensitivity (85.91%) and precision (100%) of the accelerometer were assessed. Animals were exposed to an ABA-type experimental design: A1 and A2: complex enclosure; B: decreased complexity (each stage lasted 24 h). An increase in total activity (%) was revealed using the accelerometer (26.15 ± 1.50, 29.29 ± 2.25, and 35.36 ± 3.15, respectively). Similar activity levels were detected using video analysis. The results demonstrate that the use of the accelerometer is reliable to determine the activity. Considering that the zoo-housed lesser anteaters exhibit a cathemeral activity pattern, this study contributes to easily monitoring their activities and responses to different management procedures supporting welfare programs, as well as ex situ conservation.

Direct-to-Consumer Genetic Testing on Social Media: Topic Modeling and Sentiment Analysis of YouTube Users' Comments.

With direct-to-consumer (DTC) genetic testing enabling self-responsible access to novel information on ancestry, traits, or health, consumers often turn to social media for assistance and discussion. YouTube, the largest social media platform for videos, offers an abundance of DTC genetic testing-related videos. Nevertheless, user discourse in the comments sections of these videos is largely unexplored. This study aims to address the lack of knowledge concerning user discourse in the comments sections of DTC genetic testing-related videos on YouTube by exploring topics discussed and users' attitudes toward these videos. We employed a 3-step research approach. First, we collected metadata and comments of the 248 most viewed DTC genetic testing-related videos on YouTube. Second, we conducted topic modeling using word frequency analysis, bigram analysis, and structural topic modeling to identify topics discussed in the comments sections of those videos. Finally, we employed Bing (binary), National Research Council Canada (NRC) emotion, and 9-level sentiment analysis to identify users' attitudes toward these DTC genetic testing-related videos, as expressed in their comments. We collected 84,082 comments from the 248 most viewed DTC genetic testing-related YouTube videos. With topic modeling, we identified 6 prevailing topics on (1) general genetic testing, (2) ancestry testing, (3) relationship testing, (4) health and trait testing, (5) ethical concerns, and (6) YouTube video reaction. Further, our sentiment analysis indicates strong positive emotions (anticipation, joy, surprise, and trust) and a neutral-to-positive attitude toward DTC genetic testing-related videos. With this study, we demonstrate how to identify users' attitudes on DTC genetic testing by examining topics and opinions based on YouTube video comments. Shedding light on user discourse on social media, our findings suggest that users are highly interested in DTC genetic testing and related social media content. Nonetheless, with this novel market constantly evolving, service providers, content providers, or regulatory authorities may still need to adapt their services to users' interests and desires.

Fast Decision Algorithm of CU Size for HEVC Intra-Prediction Based on a Kernel Fuzzy SVM Classifier

High Efficiency Video Coding (HEVC) achieves a significant improvement in compression efficiency at the cost of extremely high computational complexity. Therefore, large-scale and wide deployment applications, especially mobile real-time video applications under low-latency and power-constrained conditions, are more challenging. In order to solve the above problems, a fast decision method for intra-coding unit size based on a new fuzzy support vector machine classifier is proposed in this paper. The relationship between the depth levels of coding units is accurately expressed by defining the cost evaluation criteria of texture and non-texture rate-distortion cost. The fuzzy support vector machine is improved by using the information entropy measure to solve the negative impact of data noise and the outliers problem. The proposed method includes three stages: the optimal coded depth level “0” early decision, coding unit depth early skip, and optimal coding unit early terminate. In order to further improve the rate-distortion complexity optimization performance, more feature vectors are introduced, including features such as space complexity, the relationship between coding unit depths, and rate-distortion cost. The experimental results showed that, compared with the HEVC reference test model HM16.5, the proposed algorithm can reduce the encoding time of various test video sequences by more than 53.24% on average, while the Bjontegaard Delta Bit Rate (BDBR) only increases by 0.82%. In addition, the proposed algorithm is better than the existing algorithms in terms of comprehensively reducing the computational complexity and maintaining the rate-distortion performance.

Teaching Video NeuroImage: Subacute Cerebellar Ataxia in an Adolescent With Antibodies Against Metabotropic Glutamate Receptor Type 1.

A 15-year-old boy developed progressive cerebellar dysfunction over 3 weeks. Examination showed ataxic gait, unsteady tandem gait, horizontal nystagmus, intention tremor, and ataxia on heel-toe-shin testing (Video 1, [links.lww.com/WNL/C323][1]). Dysdiadochokinesia and dysarthria were found but not illustrated in the video. Neuroimaging and CSF biochemistry was normal. Serum and CSF metabotropic glutamate receptor type 1 (anti-mGluR1) autoantibodies were found. His cerebellar function improved markedly within 3 months of initiating immunotherapy (Video 1, [links.lww.com/WNL/C323][1]). The median age at onset of anti-mGluR1 encephalitis is 55 years.1,2 Paraneoplastic syndromes should be considered, but anti-mGluR1 encephalitis is more often autoimmune in younger patients.1,2 [1]: http://links.lww.com/WNL/C323

Smoke detection in video using convolutional neural networks and efficient spatio-temporal features

Fire detection in its early stages is of a great importance in different environmental related applications. Among the visual signs of fire, smoke appears earlier than the flames in many cases, and quickly reaches the environment. Thus, it can be used for early detection of fire using machine vision techniques. Existing approaches have tried to do it either by traditional machine learning methods applying various combinations of color, texture, and motion features, or by deep learning-based methods that can automatically capture the smoke features from images. However, the former approaches face number of challenges due to the transparent nature of smoke and its variant visual appearance in different environments, and the later ones are not able to capture motion characteristics of smoke, so, their efficiency in various environmental conditions is still problematic and often cause false alarms. In this study, we aim to introduce a hybrid approach that is based on deep learning, spatio, and spatio-temporal characteristics of the smoke. Doing so, we use all the strengths of these techniques to detect the smoke as accurately as possible. The proposed method consists of four stages: 1) moving pixels are extracted from input images by an efficient motion detection scheme; 2) the extracted moving areas are given individually to a tailored convolutional neural network to identify candidate smoke regions; 3) an efficient combination of spatial and spatio-temporal features is extracted from each candidate region based on the distinct characteristics of smoke; 4) a support vector machine classifier is used to further classify real smoke from non-smoke regions using the extracted features. The proposed method is implemented using Python programming language, and extensive experiments conducted on “Visor”, “Bilkent”, and “Yuan” benchmark datasets which show it has high performance and accuracy. The results also indicate that its reliability is far better than the competitors in terms of false alarm rate. The average accuracy and false positive rates obtained on 10 testing videos are 97.63% and 3.8%, respectively. Also, the proposed method is able to detect both white and black smokes which, to our best knowledge, has not been addressed in any of the related researches.

Unsupervised video object segmentation: an affinity and edge learning approach

This paper presents a new approach, called TMNet, to solve unsupervised video object segmentation (UVOS) problem. The UVOS is still a challenging problem as prior methods suffer from issues like generalization errors in unseen test videos, over reliance on optic flow, and capturing fine details at object boundaries. These issues make the UVOS an ill-defined problem, particularly in presence of multiple objects. Our focus is to constrain the problem and improve the segmentation results by fusion of multiple available cues such as appearance and motion, as well as image and flow edges. To constrain the problem, instead of predicting segmentation directly, we predict affinities between neighbouring pixels for being part of the same object and cluster those to obtain category agnostic segmentation. To further improve the segmentation, we fuse multiple-sources of information through a novel Temporal Motion Attention (TMA) module that uses neural attention to learn powerful spatio-temporal features. In addition, we also design an edge refinement module (using image and optic flow edges) to refine and improve the accuracy of object segmentation boundaries. The overall framework is capable of segmenting and finding accurate objects’ boundaries without any heuristic post processing. This enables the method to be used for unseen videos. Experimental results on challenging DAVIS16 and multi object DAVIS17 datasets show that our proposed TMNet performs favorably compared to the state-of-the-art methods without post processing.

Machine vision-based testing action recognition method for robotic testing of mobile application

The explosive growth and rapid version iteration of various mobile applications have brought enormous workloads to mobile application testing. Robotic testing methods can efficiently handle repetitive testing tasks, which can compensate for the accuracy of manual testing and improve the efficiency of testing work. Vision-based robotic testing identifies the types of test actions by analyzing expert test videos and generates expert imitation test cases. The mobile application expert imitation testing method uses machine learning algorithms to analyze the behavior of experts imitating test videos, generates test cases with high reliability and reusability, and drives robots to execute test cases. However, the difficulty of estimating multi-dimensional gestures in 2D images leads to complex algorithm steps, including tracking, detection, and recognition of dynamic gestures. Hence, this article focuses on the analysis and recognition of test actions in mobile application robot testing. Combined with the improved YOLOv5 algorithm and the ResNet-152 algorithm, a visual modeling method of mobile application test action based on machine vision is proposed. The precise localization of the hand is accomplished by injecting dynamic anchors, attention mechanism, and the weighted boxes fusion in the YOLOv5 algorithm. The improved algorithm recognition accuracy increased from 82.6% to 94.8%. By introducing the pyramid context awareness mechanism into the ResNet-152 algorithm, the accuracy of test action classification is improved. The accuracy of the test action classification was improved from 72.57% to 76.84%. Experiments show that this method can reduce the probability of multiple detections and missed detection of test actions, and improve the accuracy of test action recognition.

Automatic Vehicle Identification and Classification Model Using the YOLOv3 Algorithm for a Toll Management System

Vehicle identification and classification are some of the major tasks in the areas of toll management and traffic management, where these smart transportation systems are implemented by integrating various information communication technologies and multiple types of hardware. The currently shifting era toward artificial intelligence has also motivated the implementation of vehicle identification and classification using AI-based techniques, such as machine learning, artificial neural network and deep learning. In this research, we used the deep learning YOLOv3 algorithm and trained it on a custom dataset of vehicles that included different vehicle classes as per the Indian Government’s recommendation to implement the automatic vehicle identification and classification for use in the toll management system deployed at toll plazas. For faster processing of the test videos, the frames were saved at a certain interval and then the saved frames were passed through the algorithm. Apart from toll plazas, we also tested the algorithm for vehicle identification and classification on highways and urban areas. Implementing automatic vehicle identification and classification using traditional techniques is a highly proprietary endeavor. Since YOLOv3 is an open-standard-based algorithm, it paves the way to developing sustainable solutions in the area of smart transportation.

Recognition of Freezing of Gait in Parkinson's Disease Based on Machine Vision.

BackgroundFreezing of gait (FOG) is a common clinical manifestation of Parkinson’s disease (PD), mostly occurring in the intermediate and advanced stages. FOG is likely to cause patients to fall, resulting in fractures, disabilities and even death. Currently, the pathogenesis of FOG is unclear, and FOG detection and screening methods have various defects, including subjectivity, inconvenience, and high cost. Due to limited public healthcare and transportation resources during the COVID-19 pandemic, there are greater inconveniences for PD patients who need diagnosis and treatment.ObjectiveA method was established to automatically recognize FOG in PD patients through videos taken by mobile phone, which is time-saving, labor-saving, and low-cost for daily use, which may overcome the above defects. In the future, PD patients can undergo FOG assessment at any time in the home rather than in the hospital.MethodsIn this study, motion features were extracted from timed up and go (TUG) test and the narrow TUG (Narrow) test videos of 50 FOG-PD subjects through a machine learning method; then a motion recognition model to distinguish between walking and turning stages and a model to recognize FOG in these stages were constructed using the XGBoost algorithm. Finally, we combined these three models to form a multi-stage FOG recognition model.ResultsWe adopted the leave-one-subject-out (LOSO) method to evaluate model performance, and the multi-stage FOG recognition model achieved a sensitivity of 87.5% sensitivity and a specificity of 79.82%.ConclusionA method to realize remote PD patient FOG recognition based on mobile phone video is presented in this paper. This method is convenient with high recognition accuracy and can be used to rapidly evaluate FOG in the home environment and remotely manage FOG-PD, or screen patients in large-scale communities.

Acute Unilateral Peripheral Vestibulopathy After COVID-19 Vaccination: Initial Experience in a Tertiary Neurotology Center.

ObjectiveThe aim of the present study was to identify patients who developed acute unilateral peripheral vestibulopathy (AUPVP) after COVID-19 vaccination.MethodsFor this single-center, retrospective study, we screened the medical records of our tertiary interdisciplinary neurotology center for patients who had presented with AUPVP within 30 days after COVID-19 vaccination (study period: 1 June−31 December 2021). The initial diagnosis of AUPVP was based on a comprehensive bedside neurotological examination. Laboratory vestibular testing (video head impulse test, cervical and ocular vestibular evoked myogenic potentials, dynamic visual acuity, subjective visual vertical, video-oculography, caloric testing) was performed 1–5 months later.ResultsTwenty-six patients were diagnosed with AUPVP within the study period. Of those, n = 8 (31%) had developed acute vestibular symptoms within 30 days after COVID-19 vaccination (mean interval: 11.9 days, SD: 4.8, range: 6–20) and were thus included in the study. The mean age of the patients (two females, six males) was 46 years (SD: 11.7). Seven patients had received the Moderna mRNA vaccine and one the Pfizer/BioNTech mRNA vaccine. All patients displayed a horizontal(-torsional) spontaneous nystagmus toward the unaffected ear and a pathological clinical head impulse test toward the affected ear on initial clinical examination. Receptor-specific laboratory vestibular testing performed 1–5 months later revealed recovery of vestibular function in two patients, and heterogeneous lesion patterns of vestibular endorgans in the remaining six patients.Discussion and ConclusionsThe present study should raise clinicians' awareness for AUPVP after COVID-19 vaccination. The relatively high fraction of such cases among our AUPVP patients may be due to a certain selection bias at a tertiary neurotology center. Patients presenting with acute vestibular symptoms should be questioned about their vaccination status and the date of the last vaccination dose. Furthermore, cases of AUPVP occurring shortly after a COVID-19 vaccination should be reported to the health authorities to help determining a possible causal relationship.

Video Anomaly Detection Based on Convolutional Recurrent AutoEncoder.

As an essential task in computer vision, video anomaly detection technology is used in video surveillance, scene understanding, road traffic analysis and other fields. However, the definition of anomaly, scene change and complex background present great challenges for video anomaly detection tasks. The insight that motivates this study is that the reconstruction error for normal samples would be lower since they are closer to the training data, while the anomalies could not be reconstructed well. In this paper, we proposed a Convolutional Recurrent AutoEncoder (CR-AE), which combines an attention-based Convolutional Long–Short-Term Memory (ConvLSTM) network and a Convolutional AutoEncoder. The ConvLSTM network and the Convolutional AutoEncoder could capture the irregularity of the temporal pattern and spatial irregularity, respectively. The attention mechanism was used to obtain the current output characteristics from the hidden state of each Covn-LSTM layer. Then, a convolutional decoder was utilized to reconstruct the input video clip and the testing video clip with higher reconstruction error, which were further judged to be anomalies. The proposed method was tested on two popular benchmarks (UCSD ped2 Dataset and Avenue Dataset), and the experimental results demonstrated that CR-AE achieved 95.6% and 73.1% frame-level AUC on two public datasets, respectively.

Automatic Measurement Method of Slump Flow of Cement Paste Based on Dynamic Image Processing Technology

The slump flow and flow time T200 are the main parameters to evaluate the rheological properties of cement paste. Generally, the manual measurement method is used and it is difficult to get T200 accurately. In this paper, an automatic measurement method of slump flow based on dynamic image processing technology is studied. Firstly, the cement paste flowability test video is divided into frames every 100 ms; secondly, based on the principle of perspective transformation, an automatic point selection method is proposed to correct the frame image to solve the problem of shooting angle; thirdly, the watershed algorithm based on distance transformation is used to segment the boundary of the cement paste area, and the slump flow is calculated according to the polar coordinates of the boundary; lastly, the relationship curve between slump flow and time is automatically output, and the slump flow at any time is obtained. The method is verified by nine groups of cement paste flowability tests. The results show that this method can fastly and accurately obtain the slump flow and flow time T200. Compared with the traditional manual measurement method, the measurement error of slump flow is less than 2%, and the measurement error of flow time T200 is less than 8%. The method enables real-time dynamic measurement of the slump flow.

633-P: Families' Lived Experience Guides Intervention Development: Addressing the Psychosocial Needs of Families in the First Year after Diagnosis

A diagnosis of T1D can be overwhelming. Offering psychosocial support throughout the first year may facilitate family adjustment. To our knowledge, no interventions exist that promote psychosocial adjustment in families immediately following diagnosis. Family-based interventions are rarely developed with a focus on the experiences of the families who have lived through the diagnosis. This study offers a novel approach to developing a family-based intervention for youth with T1D, with content developed from the lived experiences of youth and their parents. The goal of Teaming up for T1D with Telehealth (Triple T) is to support families post-diagnosis, combining brief, targeted telehealth sessions and access to a video library depicting common family experiences during the first year. We conducted age specific focus groups to explore challenges, fears, successes, and advice of youth and their families, diagnosed within the past 2 years. Children (8-12 years; n= 10) ; teens (13-17 years; n= 11) ; their caregivers (n= 27) and parents of children 7 or younger (n= 12) participated. Main themes were sorted into topics to be addressed by telehealth visits or videos. These themes informed the development of 20 videos with age-specific themes. There were five main topics: Reassurance that they will be “Okay”; Strategies for getting to “Okay”; Managing activities; Handling disclosure and questions; and Family teamwork. Test videos were reviewed by the original focus group participants for additional stakeholder feedback. Final videos were filmed with professional actors to be used in conjunction with telehealth sessions during the intervention. Using stakeholder experience in addition to clinical experience and empirical research to inform interventions represents a novel approach to developing interventions that may directly address the needs of families and inform future interventions and education following a T1D diagnosis. Disclosure K.P.Garza: None. K.R.Howard: None. J.Weissberg-benchell: None. M.Feldman: None. Funding Juvenile Diabetes Research Foundation

УСКОРЕНИЕ ПРЯМОГО ПРОХОДА ПРИ РЕАЛИЗАЦИИ СНС НА ОГРАНИЧЕННОМ ВЫЧИСЛИТЕЛЬНОМ РЕСУРСЕ

The work is devoted to the optimization of the neural network architecture for its launch ona limited computing resource. Several optimization approaches are considered, estimates of thecomplexity and execution time of the forward pass of the neural network are given. Comparativeestimates of the complexity of the network using different optimization approaches are given.The paper presents an analysis of the selected network architecture, and estimates of the computationalcomplexity of individual components (modules) of the architecture are obtained. An analysisof possible optimization methods for each module was made. The parameters of the consideredmodules, the sizes of the input and output tensors are described. Several architectures were testedto optimize the feature extraction module, ResNet 50, ResNet 18, MobileNet v3 small, MobileNetv3 large. A comparative analysis of the computational complexity and execution time of the forwardpass for each architecture is presented. Forward pass times were measured on Nvidia'sJetson AGX Xaver embedded computing device. Estimates of the execution time of the direct passfor each module of the considered neural networks are presented. The paper presents the results ofcomparing neural network accuracy estimates before and after architecture optimization. The testdata set consists of 100 video recordings. 5 different typical objects are involved in test videos,10 different scenarios are recorded for each object class. For each of the developed architectures,accuracy estimates were obtained, and a comparative analysis was made.

Evaluation of methylenetetrahydrofolate reductase and S-adenosyl-methionine level in male infertility: A case-control study.

BackgroundMethylenetetrahydrofolate reductase enzyme (MTHFR) plays a key role in regulating folate balance, converting homocysteine to methionine, and producing s-adenosylmethionine (SAM) that plays a role in the methylation process.ObjectiveThis study aimed to determine MTHFR activity and SAM level in men with normozoospermia and oligozoospermia.Materials and Methods30 oligozoospermic and 30 normozoospermic men as controls were enrolled in this case-control study. Semen analysis was conducted according to the world health organization criteria. All semen samples were collected after 3-5 days of sexual abstinence. The sperms were evaluated by sperm test video software. All subjects SAM level was measured by enzyme-linked immunosorbent assay kit, and MTHFR were measured manually.Results2 groups had a significant difference in sperm morphology (p = 0.02), concentration (p = 0.02) and motility (p = 0.03). The MTHFR activity in normozoospermic and oligozoospermic groups had significantly differences (p = 0.01). The level of SAM in the semen of oligozoospermic men was statistically lower than normozoospermic men (p = 0.03). Also, there was a positive association between MTHFR enzyme activity and SAM level in the normozoospermia group (p = 0.02, β = 0.67) and oligozoospermia group (p = 0.03, β = 0.54).ConclusionMTHFR activity and SAM concentration were statistically lower in oligozoospermia men. It seems they can affect sperm concentration, morphology, and motility.

Background segmentation in difficult weather conditions.

Background segmentation is a process in which an algorithm removes the static background from an image. This allows only a changing section of the image. This process is important for motion detection or object tracking. In this article, an approach is proposed to compare several existing algorithms for background segmentation under severe weather conditions. Three weather conditions were tested: falling snow, rain and a sunny windy day. The test algorithms were executed on a test video containing frames collected by a dedicated Raspberry Pi camera. The frames used in the tests included cars, bicycles, motorcycles, people, and trees. Preliminary results from these tests show interesting differences in detail detection and detection noise.

Dense Semantics-Assisted Networks for Video Action Recognition

Most existing action recognition approaches directly leverage the video-level features to recognize human actions from videos. Although these methods have made remarkable progress, the accuracy is still unsatisfied. When the test video involves complex backgrounds and activities, existing methods usually suffer from a significant drop in accuracy. Human action is inherently a high-level concept. Merely applying a video classification model without a detailed semantic understanding of the video content, e.g., objects, scene context, object motions, object interactions, is inadequate to tackle the challenges for action recognition. Fine-level semantic understanding of videos generates elementary semantic concepts from the raw video data, such as the semantics of objects and background regions. It can be employed to bridge the gap between the raw video data and the high-level concept of human actions. In this work, we leverage dense semantic segmentation masks, which encode rich semantic details, provide extra information for the network training, and improve the performance of action recognition. We propose a novel deep architecture which is named as Dense Semantics-Assisted Convolutional Neural Networks (DSA-CNNs) to effectively utilize dense semantic information of video by a bottom-up attention way in the spatial stream, while by the way of branch fusion in the temporal stream. To verify the effectiveness of our approach, we conduct extensive experiments on publicly available datasets – UCF101, HMDB51, and Kinetics. The experimental results demonstrate that our approach substantially improves existing methods and achieves very competitive performance. It also shows that our approach is superior to other related methods that utilize extra information for action recognition.

Development and implementation of a tool for measuring the training effectiveness of the patient-centered consultation model.

Background: The patient-centered consultation model comprises four elements: exploring health, illness and disease experiences, understanding the whole person, finding common ground, and enhancing the patient-doctor relationship. This method is taught at the course in general practice at Copenhagen University. The aim of the study was to develop a simple tool consisting of a questionnaire about the patient-centered elements and a test video consultation. The outcome is the change in the students' ability to identify these elements. Used as a pre-course and post-course test it can inform the teachers which elements of the patient-centered consultation need intensifying in the teaching. Methods: The students from a course in general practice volunteered to participate in all steps of the development. They took part in individual interviews to select items from an already existing questionnaire (DanSCORE). The preliminary questionnaire was tested for face and content validity, pilot-tested and tested for test-retest reliability. All video consultations were transcribed and assessed for patient-centered elements through a conversation analysis. The videos showed medical students seeing real patients. Results: The preliminary version of the questionnaire (called DanOBS) had 23 items. In the subsequent interviews, items were reduced to 17, each with three response options. After a pilot test, the questionnaire was further reduced to 13 items, all strictly relevant to the model and with two response options. The final questionnaire had acceptable test-retest reliability. The number of test consultation videos underwent a reduction from six videos to one. Conclusions: The DanOBS combined with a test video consultation, used as a pre-and post-course test demonstrates for teachers which elements in the patient-centered consultation need to be intensified in the teaching.

State-of-the-art violence detection techniques in video surveillance security systems: a systematic review.

We investigate and analyze methods to violence detection in this study to completely disassemble the present condition and anticipate the emerging trends of violence discovery research. In this systematic review, we provide a comprehensive assessment of the video violence detection problems that have been described in state-of-the-art researches. This work aims to address the problems as state-of-the-art methods in video violence detection, datasets to develop and train real-time video violence detection frameworks, discuss and identify open issues in the given problem. In this study, we analyzed 80 research papers that have been selected from 154 research papers after identification, screening, and eligibility phases. As the research sources, we used five digital libraries and three high ranked computer vision conferences that were published between 2015 and 2021. We begin by briefly introducing core idea and problems of video-based violence detection; after that, we divided current techniques into three categories based on their methodologies: conventional methods, end-to-end deep learning-based methods, and machine learning-based methods. Finally, we present public datasets for testing video based violence detectionmethods’ performance and compare their results. In addition, we summarize the open issues in violence detection in videoand evaluate its future tendencies.