scholarly journals AGTH-Net: Attention-Based Graph Convolution-Guided Third-Order Hourglass Network for Sports Video Classification

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Ming Gao ◽  
Weiwei Cai ◽  
Runmin Liu
Keyword(s):  
Video On Demand ◽  
Attention Mechanism ◽  
Classification Model ◽  
Video Classification ◽  
Third Order ◽  
Sports Video ◽  
Feature Extracting ◽  
Convolution Model ◽  
Wide Range ◽  
The Impact

As a hot research topic, sports video classification research has a wide range of applications in switched TV, video on demand, smart TV, and other fields and is closely related to people’s lives. Under this background, sports video classification research has aroused great interest in people. However, the existing methods usually use manual video classification, which the workers themselves often influence. It is challenging to ensure the accuracy of the results, leading to the wrong classification. Due to these limitations, we introduce neural network technology to the automatic classification of sports. This paper proposed a novel attention-based graph convolution-guided third-order hourglass network (AGTH-Net) classification model. First, we designed a kind of figure convolution model based on the attention mechanism. The model is the key to introduce the attention mechanism for neighborhood node weights’ allocation. It reduces the impact of error nodes in the neighborhood while avoiding manual weight assignment. Second, according to the sports complex video image characteristics, we use the third-order hourglass network structure. It is used for the extraction and fusion of multiscale characteristics of sports. In addition, in the hourglass, internal network residual-intensive modules are introduced, realizing characteristics in different levels of network transfer and reuse. It is helpful for maximum details to feature extracting and enhancing the network expression ability. Comparison and ablation experiments are also carried out to prove the effectiveness and superiority of the proposed algorithm.

scholarly journals An Extended Text Combination Classification Model for Short Video Based on Albert

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Yi Liu ◽  
Yue Zhang ◽  
Haidong Hu ◽  
Xiaodong Liu ◽  
Lun Zhang ◽  
...  
Keyword(s):  
Text Classification ◽  
Rapid Development ◽  
Computational Cost ◽  
Attention Mechanism ◽  
Classification Model ◽  
Classification Methods ◽  
Video Classification ◽  
Short Video ◽  
Text Information ◽  
Key Frames

With the rise and rapid development of short video sharing websites, the number of short videos on the Internet has been growing explosively. The organization and classification of short videos have become the basis for the effective use of short videos, which is also a problem faced by major short video platforms. Aiming at the characteristics of complex short video content categories and rich extended text information, this paper uses methods in the text classification field to solve the short video classification problem. Compared with the traditional way of classifying and understanding short video key frames, this method has the characteristics of lower computational cost, more accurate classification results, and easier application. This paper proposes a text classification model based on the attention mechanism of multitext embedding short video extension. The experiment first uses the training language model Albert to extract sentence-level vectors and then uses the attention mechanism to study the text information in various short video extensions in a short video classification weight factor. And this research applied Google’s unsupervised data augmentation (UDA) method based on unsupervised data, creatively combining it with the Chinese knowledge graph, and realized TF-IDF word replacement. During the training process, we introduced a large amount of unlabeled data, which significantly improved the accuracy of model classification. The final series of related experiments is aimed at comparing with the existing short video title classification methods, classification methods based on video key frames, and hybrid methods, and proving that the method proposed in this article is more accurate and robust on the test set.

scholarly journals Precision QCD phenomenology of exotic spin-2 search at the LHC

2021 ◽  
Vol 2021 (4) ◽  
Author(s):  
Goutam Das ◽  
M. C. Kumar ◽  
Kajal Samanta
Keyword(s):  
Hadron Collider ◽  
Form Factors ◽  
Phenomenological Analysis ◽  
Lepton Pair ◽  
Leading Order ◽  
Third Order ◽  
Wide Range ◽  
Dependent Form ◽  
The Impact ◽  
Leading Logarithm

Abstract The complete next-to-next-to leading order (NNLO) QCD correction matched with next-to-next-to leading logarithm (NNLL) has been studied for Drell-Yan production via spin-2 particle at the Large hadron collider (LHC). We consider generic spin-2 particle which couples differently to quarks and gluons (non-universal scenario). The threshold enhanced analytical coefficient has been obtained up to third order using the universal soft function and the process dependent form factors at the same order. We performed a detailed phenomenological analysis and gave a prediction for the 13 TeV LHC for the search of such BSM signature. We found that the resummed result gives sizeable corrections over a wide range of invariant mass of the lepton pair. The scale variation also stabilizes at this order and reduces to 4%. As a by-product, we also provide ingredients for third-order soft-virtual (SV) prediction as well as resummation and study the impact on LHC searches.

scholarly journals Big Data and Deep Learning-Based Video Classification Model for Sports

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Lin Wang ◽  
Haiyan Zhang ◽  
Guoliang Yuan
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Short Term Memory ◽  
Classification Model ◽  
Video Classification ◽  
Short Term ◽  
Term Memory ◽  
Sports Video ◽  
Human Movements

Information technologies such as deep learning, big data, cloud computing, and the Internet of Things provide key technical tools to drive the rapid development of integrated manufacturing. In recent years, breakthroughs have been made in big data analysis using deep learning. The research on the sports video high-precision classification model in this paper, more specifically, is the automatic understanding of human movements in free gymnastics videos. This paper will combine knowledge related to big data-based computer vision and deep learning to achieve intelligent labeling and representation of specific human movements present in video sequences. This paper mainly implements an automatic narrative based on long- and short-term memory networks to achieve the classification of sports videos. In the classical video description model S2VT, long- and short-term memory networks are used to learn the mapping relationship between word sequences and video frame sequences. In this paper, we introduce an attention mechanism to highlight the importance of keyframes that determine freestyle gymnastic movements. In this paper, a dataset of freestyle gymnastics breakdown movements for professional events is built. Experiments are conducted on the data and the self-constructed dataset, and the planned sampling method is applied to eliminate the differences between the training decoder and the prediction decoder. The experimental results show that the improved method in this paper can improve the accuracy of sports video classification. The video classification model based on big data and deep learning is to provide users with a better user experience and improve the accuracy of video classification. Also, in the experiments of this paper, the effect of extracting features for the classification of different lifting sports models is compared, and the effect of feature extraction network on the automatic description of free gymnastic movements is analyzed.

scholarly journals Analysis of Volleyball Video Intelligent Description Technology Based on Computer Memory Network and Attention Mechanism

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Zhongzi Zhang
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Video Analysis ◽  
Learning Algorithm ◽  
Attention Mechanism ◽  
Extraction Rate ◽  
Sports Video ◽  
Deep Learning Algorithm ◽  
Memory Network ◽  
The Impact

There are some problems in the process of video intelligent description and analysis of volleyball, such as poor effective information extraction rate and poor dynamic tracking effect. Based on this, combined with long-term and short-term memory network and attention mechanism, this paper designs an intelligent description model of volleyball video based on deep learning algorithm and studies how to improve the extraction rate of volleyball video information through intelligent detection hardware and image recognition technology. This paper first introduces the application of image recognition technology and deep learning algorithm in the intelligent description of volleyball video, then designs the volleyball video and image recognition model based on deep learning algorithm according to the requirements of volleyball video intelligent description, and selects three correlation factors related to the impact indicators of volleyball skills. This study selects three characteristic parameters associated with volleyball video analysis indexes, namely, take-off, bounce, and hand movement, combined with image sensing hardware assisted sensor network to realize real-time monitoring of action state in volleyball video analysis system. The experimental results show that, compared with the current mainstream sports video intelligent analysis and image recognition methods with data analysis as the core, the intelligent volleyball sports video intelligent description and image recognition system based on the integration of deep learning algorithm and sensor hardware assistance has the advantages of good detection effect, high data effectiveness, low cost, and high efficiency of volleyball sports video analysis. It can effectively improve the efficiency of volleyball video intelligent description.

Monitoring People Emotions and Symptoms from Arabic Tweets during the COVID-19 Pandemic (Preprint)

2020 ◽  
Author(s):  
Ali Al-Laith ◽  
Mamdouh Alenezi
Keyword(s):  
Monitoring System ◽  
Short Term Memory ◽  
Classification Model ◽  
World Health ◽  
Emotion Detection ◽  
Health Crisis ◽  
Wide Range ◽  
The World ◽  
Accuracy Result ◽  
The Impact

BACKGROUND COVID-19 started from Wuhan, China, in late December 2019, and is caused by the Corona Virus. It swept most of the world countries with confirmed cases and deaths. The World Health Organization (WHO) declared the virus as a pandemic on March 11th, 2020 due to its widespread transmission. A public health crisis was declared in specific regions and notional wide by governments all around the world. Citizens go through a wide range of emotions, such as fear of shortage of food, Anger at the performance of governments and health authorities in facing the virus, sadness over the death of a friend or relative, etc. OBJECTIVE We present a monitoring system of citizen’s concerns using emotion detection in Twitter data. We also track public emotions and link these emotions with COVID-19 symptoms. We aim to show the effect of emotion monitoring on improving people's daily health behavior and reduce the spread of negative emotions that affect the mental health of the citizens. METHODS We use Twitter API to collect and annotate 5.5M tweets in the period from January 2020 to August 2020. Two deep learning classifiers namely Convolutional Neural Network (CNN) and Long-short Term Memory (LSTM) employed to classify all tweets into six emotion classes (Anger, Disgust,Fear, Joy, Sadness, and Surprise) and two types (symptom and non-symptom tweets). RESULTS Our LSTM based text classification model outperforms the CNN model in emotion and symptom classification. We achieved a significant performance on multiclass classification (emotion detection) with an accuracy result of 91%. We also achieved an accuracy result of 88% on binary classification (symptom detection). The monitoring system shows that most of the tweets were posted in March. The anger and fear emotions have the highest number of tweets and user interactions after the joy emotion. The results of user interaction monitoring show that people use likes and replies to interact with non-symptom tweets while they use re-tweets to propagate tweets that mention any of the COVID-19 symptoms. CONCLUSIONS The study helps the governments and decision-makers to prove or deny these feelingsand discover other symptoms associated with the symptoms that were declared by the WHO. It can also help in the understanding of the people’s mental and emotional issues to address them before the impact of disease anxiety becomes harmful in itself.

Spatial-Temporal Feature-Based Sports Video Classification

2021 ◽  
Vol 12 (4) ◽  
pp. 79-97
Author(s):  
Zengkai Wang
Keyword(s):  
Spatial Attention ◽  
Classification Accuracy ◽  
Short Term Memory ◽  
Attention Mechanism ◽  
Video Data ◽  
Video Frame ◽  
Video Classification ◽  
Temporal Attention ◽  
Sports Video ◽  
Average Classification Accuracy

Video classification has been an active research field of computer vision in last few years. Its main purpose is to produce a label that is relevant to the video given its frames. Unlike image classification, which takes still pictures as input, the input of video classification is a sequence of images. The complex spatial and temporal structures of video sequence incur understanding and computation difficulties, which should be modeled to improve the video classification performance. This work focuses on sports video classification but can be expanded into other applications. In this paper, the authors propose a novel sports video classification method by processing the video data using convolutional neural network (CNN) with spatial attention mechanism and deep bidirectional long short-term memory (BiLSTM) network with temporal attention mechanism. The method first extracts 28 frames from each input video and uses the classical pre-trained CNN to extract deep features, and the spatial attention mechanism is applied to CNN features to decide ‘where' to look. Then the BiLSTM is utilized to model the long-term temporal dependence between video frame sequences, and the temporal attention mechasim is employed to decide ‘when' to look. Finally, the label of the input video is given by the classification network. In order to evaluate the feasibility and effectiveness of the proposed method, an extensive experimental investigation was conducted on the open challenging sports video datasets of Sports8 and Olympic16; the results show that the proposed CNN-BiLSTM network with spatial temporal attention mechanism can effectively model the spatial-temporal characteristics of video sequences. The average classification accuracy of the Sports8 is 98.8%, which is 6.8% higher than the existing method. The average classification accuracy of 90.46% is achieved on Olympic16, which is about 18% higher than the existing methods. The performance of the proposed approach outperforms the state-of-the-art methods, and the experimental results demonstrate the effectiveness of the proposed approach.

THE IMPACT OF LEADERSHIP PRACTICES TO TEAM MEMBERS’ SATISFACTION

2009 ◽  
Vol 8 (1) ◽  
Author(s):  
Chalimah .
Keyword(s):  
Conflict Resolution ◽  
Leadership Practices ◽  
Hotel Industry ◽  
Leader Behavior ◽  
Team Leader ◽  
Shop Floor ◽  
Team Members ◽  
Top Executives ◽  
Wide Range ◽  
The Impact

eamwork is becoming increasingly important to wide range of operations. It applies to all levels of the company. It is just as important for top executives as it is to middle management, supervisors and shop floor workers. Poor teamwork at any level or between levels can seriously damage organizational effectiveness. The focus of this paper was therefore to examine whether leadership practices consist of team leader behavior, conflict resolution style and openness in communication significantly influenced the team member’s satisfaction in hotel industry. Result indicates that team leader behavior and the conflict resolution style significantly influenced team member satisfaction. It was surprising that openness in communication did not affect significantly to the team members’ satisfaction.

Stress, anxiety, depression and burnout in frontline health care workers during COVID-19 pandemic: a brief systematic review and new data from Russia

2021 ◽  
Author(s):  
Ekaterina Mosolova ◽  
Dmitry Sosin ◽  
Sergey Mosolov
Keyword(s):  
Risk Factors ◽  
Systematic Review ◽  
Female Gender ◽  
Assessment Tools ◽  
Care Workers ◽  
Younger Age ◽  
Wide Range ◽  
Associated Risk Factors ◽  
Anxiety Depression ◽  
The Impact

During the COVID-19 pandemic, healthcare workers (HCWs) have been subject to increased workload while also exposed to many psychosocial stressors. In a systematic review we analyze the impact that the pandemic has had on HCWs mental state and associated risk factors. Most studies reported high levels of depression and anxiety among HCWs worldwide, however, due to a wide range of assessment tools, cut-off scores, and number of frontline participants in the studies, results were difficult to compare. Our study is based on two online surveys of 2195 HCWs from different regions of Russia during spring and autumn epidemic outbreaks revealed the rates of anxiety, stress, depression, emotional exhaustion and depersonalization and perceived stress as 32.3%, 31.1%, 45.5%, 74.2%, 37.7% ,67.8%, respectively. Moreover, 2.4% of HCWs reported suicidal thoughts. The most common risk factors include: female gender, nurse as an occupation, younger age, working for over 6 months, chronic diseases, smoking, high working demands, lack of personal protective equipment, low salary, lack of social support, isolation from families, the fear of relatives getting infected. These results demonstrate the need for urgent supportive programs for HCWs fighting COVID-19 that fall into higher risk factors groups.

A MODELING SYSTEM FOR CLIMATE CHANGE RISK ASSESSMENT, MANAGEMENT AND HEDGING IN COASTAL AREAS

2017 ◽  
Author(s):  
Sergei Soldatenko ◽  
Sergei Soldatenko ◽  
Genrikh Alekseev ◽  
Genrikh Alekseev ◽  
Alexander Danilov ◽  
...  
Keyword(s):  
Climate Change ◽  
Risk Assessment ◽  
Coastal Areas ◽  
Mitigation Strategies ◽  
System Structure ◽  
The Arctic ◽  
Risk Modeling ◽  
Wide Range ◽  
Adverse Weather ◽  
The Impact

Every aspect of human operations faces a wide range of risks, some of which can cause serious consequences. By the start of 21st century, mankind has recognized a new class of risks posed by climate change. It is obvious, that the global climate is changing, and will continue to change, in ways that affect the planning and day to day operations of businesses, government agencies and other organizations and institutions. The manifestations of climate change include but not limited to rising sea levels, increasing temperature, flooding, melting polar sea ice, adverse weather events (e.g. heatwaves, drought, and storms) and a rise in related problems (e.g. health and environmental). Assessing and managing climate risks represent one of the most challenging issues of today and for the future. The purpose of the risk modeling system discussed in this paper is to provide a framework and methodology to quantify risks caused by climate change, to facilitate estimates of the impact of climate change on various spheres of human activities and to compare eventual adaptation and risk mitigation strategies. The system integrates both physical climate system and economic models together with knowledge-based subsystem, which can help support proactive risk management. System structure and its main components are considered. Special attention is paid to climate risk assessment, management and hedging in the Arctic coastal areas.

The Management of Post-Tonsillectomy Morbidity in Patients With Sleep Apnoea

2019 ◽  
Vol 70 (10) ◽  
pp. 3738-3740
Keyword(s):  
Day Surgery ◽  
Sleep Apnoea ◽  
Integrative Approach ◽  
Multicenter Studies ◽  
Therapeutic Modalities ◽  
Advantages And Disadvantages ◽  
Obstructive Sleep ◽  
Wide Range ◽  
The Impact ◽  
Surgery Center

The Tonsillectomy in children or adults is an intervention commonly encountered in the ENT (Ear Nose and Throat) and Head and Neck surgeon practice. The current tendency is to perform this type of surgery in major ambulatory surgery centers. Two objectives are thus pursued: first of all, the increase of the patient quality of life through the reintegration into the family as quickly as possible and secondly, the expenses associated with continuous hospitalization are reduced. Any tertiary (multidisciplinary) sleep center must ensure the complete diagnosis and treatment (including surgery) of sleep respiratory disorders. Under these conditions the selection of patients and especially the implementation of the specific protocols in order to control the postoperative complications it becomes essential. The present paper describes our experience of tonsillectomy as treatment for selected patients with chronic rhonchopathy (snoring) and mild to moderate obstructive sleep apnoea. It was presented the impact of antibiotics protocols in reducing the main morbid outcomes following tonsillectomy, in our day surgery center. The obtained results can also be a prerequisite for the integrative approach of the patients with sleep apnoea who were recommended surgical treatment. Considering the wide range of therapeutic modalities used in sleep apnoea, each with its specific advantages and disadvantages, more extensive and multicenter studies are needed. Keywords: post-tonsillectomy morbidity, day surgery center, sleep disorders

Sign in / Sign up

Export Citation Format

Share Document