Pulse rate estimation based on facial videos:an evaluation and optimization of the classical methods using both self-constructed and public datasets

Pulse rate is one of the important characteristics of traditional Chinese medicine pulse diagnosis,and it is of great significance for determining the nature of cold and heat in diseases.The prediction of pulse rate based on facial video is an exciting research field for getting palpation information by observation diagnosis.However,most studies focus on optimizing the algorithm based on a small sample of participants without systematically investigating multiple influencing factors.A total of 209 participants and 2,435 facial videos,based on our self-constructed Multi-Scene Sign Dataset and the public datasets,were used to perform a multi-level and multi-factor comprehensive comparison.The effects of different datasets,blood volume pulse signal extraction algorithms,region of interests,time windows,color spaces,pulse rate calculation methods,and video recording scenes were analyzed.Furthermore,we proposed a blood volume pulse signal quality optimization strategy based on the inverse Fourier transform and an improvement strategy for pulse rate estimation based on signal-to-noise ratio threshold sliding.We found that the effects of video estimation of pulse rate in the Multi-Scene Sign Dataset and Pulse Rate Detection Dataset were better than in other datasets.Compared with Fast independent component analysis and Single Channel algorithms,chrominance-based method and plane-orthogonal-to-skin algorithms have a more vital anti-interference ability and higher robustness.The performances of the five-organs fusion area and the full-face area were better than that of single sub-regions,and the fewer motion artifacts and better lighting can improve the precision of pulse rate estimation.

MarkINeRV: A Robust Watermarking Scheme for Neural Representation for Videos Based on Invertible Neural Networks

Recent research advances in implicit neural representation have shown that a wide range of video data distributions are achieved by sharing model weights for Neural Representation for Videos(NeRV).While explicit methods exist for accurately embedding ownership or copyright information in video data,the nascent NeRV framework has yet to address this issue comprehensively.In response,this paper introduces MarkINeRV,a scheme designed to embed watermarking information into video frames using an invertible neural network watermarking approach to protect the copyright of NeRV,which models the embedding and extraction of watermarks as a pair of inverse processes of a reversible network and employs the same network to achieve embedding and extraction of watermarks.It is just that the information flow is in the opposite direction.Additionally,a video frame quality enhancement module is incorporated to mitigate watermarking information losses in the rendering process and the possibility ofmalicious attacks during transmission,ensuring the accurate extraction of watermarking information through the invertible network’s inverse process.This paper evaluates the accuracy,robustness,and invisibility of MarkINeRV through multiple video datasets.The results demonstrate its efficacy in extracting watermarking information for copyright protection of NeRV.MarkINeRV represents a pioneering investigation into copyright issues surrounding NeRV.

Estimation of peak wave period from surface texture motion in videos

Wave information retrieval from videos captured by a single camera has been increasingly applied in marine observation.However,when the camera observes ocean waves at low grazing angles,the accurate extraction of wave information from videos will be affected by the interference of the fine ripples on the sea surface.To solve this problem,this study develops a method for estimating peak wave periods from videos captured at low grazing angles.The method extracts the motion of the sea surface texture from the video and obtains the peak wave period via the spectral analysis.The calculation results captured from real-world videos are compared with those obtained from X-band radar inversion and tracking buoy movement,with maximum deviations of 8%and 14%,respectively.The analysis of the results shows that the peak wave period of the method has good stability.In addition,this paper uses a pinhole camera model to convert the displacement of the texture from pixel height to actual height and performs moving average filtering on the displacement of the texture,thus conducting a preliminary exploration of the inversion of significant wave height.This study helps to extend the application of sea surface videos.

Research on Strategies for Enhancing the Ability of Chinese German Learners to Tell Chinese Stories Through Short Videos

In the age of new media,short videos play an increasingly important role in international cultural exchange.However,German learners often encounter challenges when producing and sharing short videos due to factors such as technology and language proficiency.Such challenges can affect the professionalism and attractiveness of the videos.This study focuses on German learners at the University of Shanghai for Science and Technology.The aim of this study is to investigate students’experiences in producing short videos,identify issues through surveys and interviews,and concentrate on editing skills,language proficiency,and intercultural communication abilities.It proposes strategies for developing these skills and aims to provide insights for German and other foreign language learners in telling Chinese stories using short videos.

How Rustic Videos Influence Youth’s Linguistic Expression: An Analysis Based on Semiotics, Meme Theory and Media Spectacle Theory

The surge in popularity of rustic videos has spawned a great number of Internet memes, such as Internet trendy words growing from dialects and strange pronunciations, picture memes made from video screenshots, and mesmerizing music with a vernacular flavor. Due to their reproducibility, social interaction, and involvement, these rustic videos adhere to the fundamental logic of the propagation of online memes. Rustic videos are widely disseminated as online memes on TikTok (the Chinese version), are often reproduced and used by young people in social contact, and have become a unique linguistic symbol in modern internet culture. As a symbolic carrier that transports the consciousness of the video creator and viewer, it is widely employed in the communication and engagement of young people on a regular basis, progressively altering their linguistic expression. This specific semiotic interaction has deconstructed and recreated the conventional media culture spectacle. This research examines the influence of rustic videos on TikTok on the linguistic expressions of modern youth from the perspectives of meme theory and semiotics, as well as the impact of rustic videos on the media spectacle from the standpoint of media spectacle theory. It also examines in depth the effects of the popularity of rustic videos on China’s economy and culture.

A Multimodal Critical Discourse Analysis of Lingnan Cultural Promotional Videos on Social Media

In recent years,more and more directors of culture and tourism have taken part in the promotion of local cultural tourism by cross-dressing,talent shows,and pushing their limits on self-media platforms.This study investigates short videos of Lingnan culture promoted by directors general and deputy directors general of the Culture,Radio,Television,Tourism,and Sports Bureau of counties and cities in Guangdong Province on social media by the method of multimodal critical discourse analysis.The analysis of 33 videos shows that Lingnan culture is a domineering and confident culture,historical culture,graceful and elegant culture,and vibrant and active culture.Domineering and confident culture is embedded in the utterances and behaviors of the directors general or deputy directors general in the video.Historical culture is realized through the conversation with historical figures through time travel.Graceful and elegant culture is constructed in the depiction of sceneries and the depiction of characters’manners.Vibrant and active culture is represented in the depiction of the characters’actional process and analytical process.

The Discourse-Historical Approach of Identity Construction in Corporate Promotional Videos for External Publicity Image

Corporate identity construction of external publicity image is an important part of the development of enterprises.Based on Wodak’s discourse-historical approach,this study takes the text of COFCO’s English promotional video as the research object,analyzes the corporate brand image,media image,organizational image,and environmental image constructed by the enterprises from three steps:linguistic expression,discourse strategy,and theme to provide references for Chinese enterprises to enhance their international influence.

The Impact of Short Media Videos on Urban Tourism Marketing:Taking Zibo and Xi'an as Examples

In the era of new media,short videos as an innovative means of communication have led to significant changes in the promotion strategies of tourist cities.The prosperity of the tourism industry has a significant driving effect on local economic growth,and marketing strategies are the key to the progress of the tourism industry.Through efficient marketing methods,the visibility of tourist attractions and cities can be significantly improved,thereby attracting more tourists and injecting new vitality into the local tourism industry and the overall economy.At present,with the rapid development of short video platforms such as TikTok and the sharp increase in the number of users,short video marketing has gradually received widespread attention from industry professionals and the general public.Some cities have achieved good results in tourism marketing implemented with the help of short video platforms,prompting more cities to use short videos for marketing activities.However,short videos also negatively impact urban tourism marketing,reducing the appeal of TikTok marketing to audiences.Therefore,this article conducts in-depth research on the impact of short video media on urban tourism marketing,elaborates on the advantages,analyzes the impact,proposes strategies for the application,and hopes to provide a reference for cities to use short videos for tourism marketing.

Application Progress of Teaching in the Form of Traffic Short Videos in Nursing Education

With the rapid development of the information technology era,the teaching quality requirements continue to surge,and the mode of education in colleges and universities has also carried out certain innovations.The integration of modern information technology into the teaching process and the combination of medical content has become a new hotspot for reform and innovation of medical education at home and abroad.In this paper,we will describe the application of traffic short videos as the main teaching form in nursing education in domestic and foreign studies,and the role of the application of this teaching form in the improvement of theoretical knowledge and clinical skills of nursing students,as well as the impact on the cultivation of nursing students’professional cognition,communication skills,critical thinking,etc.,with the aim of providing new perspectives for the subsequent nursing education.

A Study on Rural Cultural Communication of Short Videos From the Perspective of Mediation-Taking the Popularization of “Village BA” (Village Basketball Association) in Qiandongnan as an Example

With the rise of new media and short videos shaping the new communication environment,rural culture has been mediated and transformed to spread to a wider region.As a cultural achievement of rural revitalization,“Village BA”(Village Basketball Association)demonstrates Chinese modernization.The use of short videos,mass rural movements,and“spectacle”spaces to attract spectators has become a key issue in the dissemination of rural culture.

Optimization of Interactive Videos Empowered the Experience of Learning Management System

The Learning management system(LMS)is now being used for uploading educational content in both distance and blended setups.LMS platform has two types of users:the educators who upload the content,and the students who have to access the content.The students,usually rely on text notes or books and video tutorials while their exams are conducted with formal methods.Formal assessments and examination criteria are ineffective with restricted learning space which makes the student tend only to read the educational contents and videos instead of interactive mode.The aim is to design an interactive LMS and examination video-based interface to cater the issues of educators and students.It is designed according to Human-computer interaction(HCI)principles to make the interactive User interface(UI)through User experience(UX).The interactive lectures in the form of annotated videos increase user engagement and improve the self-study context of users involved in LMS.The interface design defines how the design will interact with users and how the interface exchanges information.The findings show that interactive videos for LMS allow the users to have a more personalized learning experience by engaging in the educational content.The result shows a highly personalized learning experience due to the interactive video and quiz within the video.

Quantum Computing Based Neural Networks for Anomaly Classification in Real-Time Surveillance Videos

For intelligent surveillance videos,anomaly detection is extremely important.Deep learning algorithms have been popular for evaluating realtime surveillance recordings,like traffic accidents,and criminal or unlawful incidents such as suicide attempts.Nevertheless,Deep learning methods for classification,like convolutional neural networks,necessitate a lot of computing power.Quantum computing is a branch of technology that solves abnormal and complex problems using quantum mechanics.As a result,the focus of this research is on developing a hybrid quantum computing model which is based on deep learning.This research develops a Quantum Computing-based Convolutional Neural Network(QC-CNN)to extract features and classify anomalies from surveillance footage.A Quantum-based Circuit,such as the real amplitude circuit,is utilized to improve the performance of the model.As far as my research,this is the first work to employ quantum deep learning techniques to classify anomalous events in video surveillance applications.There are 13 anomalies classified from the UCF-crime dataset.Based on experimental results,the proposed model is capable of efficiently classifying data concerning confusion matrix,Receiver Operating Characteristic(ROC),accuracy,Area Under Curve(AUC),precision,recall as well as F1-score.The proposed QC-CNN has attained the best accuracy of 95.65 percent which is 5.37%greater when compared to other existing models.To measure the efficiency of the proposed work,QC-CNN is also evaluated with classical and quantum models.

Automatic Team Assignment and Jersey Number Recognition in Football Videos

Football is one of the most-watched sports,but analyzing players’per-formance is currently difficult and labor intensive.Performance analysis is done manually,which means that someone must watch video recordings and then log each player’s performance.This includes the number of passes and shots taken by each player,the location of the action,and whether or not the play had a successful outcome.Due to the time-consuming nature of manual analyses,interest in automatic analysis tools is high despite the many interdependent phases involved,such as pitch segmentation,player and ball detection,assigning players to their teams,identifying individual players,activity recognition,etc.This paper proposes a system for developing an automatic video analysis tool for sports.The proposed system is the first to integrate multiple phases,such as segmenting the field,detecting the players and the ball,assigning players to their teams,and iden-tifying players’jersey numbers.In team assignment,this research employed unsu-pervised learning based on convolutional autoencoders(CAEs)to learn discriminative latent representations and minimize the latent embedding distance between the players on the same team while simultaneously maximizing the dis-tance between those on opposing teams.This paper also created a highly accurate approach for the real-time detection of the ball.Furthermore,it also addressed the lack of jersey number datasets by creating a new dataset with more than 6,500 images for numbers ranging from 0 to 99.Since achieving a high perfor-mance in deep learning requires a large training set,and the collected dataset was not enough,this research utilized transfer learning(TL)to first pretrain the jersey number detection model on another large dataset and then fine-tune it on the target dataset to increase the accuracy.To test the proposed system,this paper presents a comprehensive evaluation of its individual stages as well as of the sys-tem as a whole.

Beyond Video Quality:Evaluation of Spatial Presence in 360-Degree Videos

With the rapid development of immersive multimedia technologies,360-degree video services have quickly gained popularity and how to ensure sufficient spatial presence of end users when viewing 360-degree videos becomes a new challenge.In this regard,accurately acquiring users’sense of spatial presence is of fundamental importance for video service providers to improve their service quality.Unfortunately,there is no efficient evaluation model so far for measuring the sense of spatial presence for 360-degree videos.In this paper,we first design an assessment framework to clarify the influencing factors of spatial presence.Related parameters of 360-degree videos and headmounted display devices are both considered in this framework.Well-designed subjective experiments are then conducted to investigate the impact of various influencing factors on the sense of presence.Based on the subjective ratings,we propose a spatial presence assessment model that can be easily deployed in 360-degree video applications.To the best of our knowledge,this is the first attempt in literature to establish a quantitative spatial presence assessment model by using technical parameters that are easily extracted.Experimental results demonstrate that the proposed model can reliably predict the sense of spatial presence.

Audio Description for Educational Videos on COVID-19 Response:A Corpus-Based Study on Linguistic and Textual Idiosyncrasies

Audio description(AD),unlike interlingual translation and interpretation,is subject to unique constraints as a spoken text.Facilitated by AD,educational videos on COVID-19 anti-virus measures are made accessible to the visually disadvantaged.In this study,a corpus of AD of COVID-19 educational videos is developed,named“Audio Description Corpus of COVID-19 Educational Videos”(ADCCEV).Drawing on the model of Textual and Linguistic Audio Description Matrix(TLADM),this paper aims to identify the linguistic and textual idiosyncrasies of AD themed on COVID-19 response released by the New Zealand Government.This study finds that linguistically,the AD script uses a mix of complete sentences and phrases,the majority being in Present Simple tense.Present participles and the“with”structure are used for brevity.Vocabulary is diverse,with simpler words for animated explainers.Third-person pronouns are common in educational videos.Color words are a salient feature of AD,where“yellow”denotes urgency,and“red”indicates importance,negativity,and hostility.On textual idiosyncrasies,coherence is achieved through intermodal components that align with the video’s mood and style.AD style varies depending on the video’s purpose,from informative to narrative or expressive.

Camera Independent Motion Deblurring in Videos Using Machine Learning

In this paper, we will be looking at our efforts to find a novel solution for motion deblurring in videos. In addition, our solution has the requirement of being camera-independent. This means that the solution is fully implemented in software and is not aware of any of the characteristics of the camera. We found a solution by implementing a Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) hybrid model. Our CNN-LSTM is able to deblur video without any knowledge of the camera hardware. This allows it to be implemented on any system that allows the camera to be swapped out with any camera model with any physical characteristics.

结合视角矫正和改进ViViT的驾驶员睡意判断方法

针对传统检测方法中摄像头视角受限问题,提出了一种结合面部姿态矫正和改进ViViT的多视角下人脸疲倦检测方法。采用Mediapipe Face Mesh定位面部三维特征点并将其矫正为正面,利用提出的FGR-ViViT模型来捕捉矫正后的眼睛、眉毛、嘴巴线条图像帧序列变化。FGR-ViViT通过在ViViT的Temporal Transformer Encoder中添加部件选择模块来捕捉特征在时间维度中的细微差异,同时融合2次dropout和改进的对比损失函数来调整样本的相似性,降低模型过拟合风险并提高泛化能力。实验结果表明,提出的方法在YawDD和DROZY矫正后的线条图像帧的测试集上,F1-分数达到了94.5%和97.6%,相较于原始人脸图像帧分别提高了3.2%和10.4%,其FGR-ViViT相较于原始ViViT分别提高了6.1%和0.7%。所提方法适用于摄像头灵活摆放的多种应用场景,对解决多视角人脸睡意判断具有积极意义。

基于开源大模型的短视频与直播AI实训系统的设计与实现

提出了一种基于开源大模型的短视频与直播AI实训系统设计方案,旨在通过集成Llama-3、Stable Diff usion、Stable Video Diff usion等先进技术,构建一个集教学与实践于一体的智能化平台,促进新媒体人才的培养。系统设计覆盖账号定位分析、剧本策划、分镜头生成至视频合成的全链路,利用ComfyUI提供用户友好的操作界面,NestJS实现高效的服务器管理,以及MySQL和MongoDB支持数据存储。经过功能测试与用户体验评估,所设计的系统有效提升了学生的实践技能与内容创作水平,具有良好的应用前景。未来发展方向包括模型的持续优化、技术升级,以及加强与产业界的合作,以更好地适配行业需求,开拓新媒体教育的未来空间。

Customized Convolutional Neural Network for Accurate Detection of Deep Fake Images in Video Collections

The motivation for this study is that the quality of deep fakes is constantly improving,which leads to the need to develop new methods for their detection.The proposed Customized Convolutional Neural Network method involves extracting structured data from video frames using facial landmark detection,which is then used as input to the CNN.The customized Convolutional Neural Network method is the date augmented-based CNN model to generate‘fake data’or‘fake images’.This study was carried out using Python and its libraries.We used 242 films from the dataset gathered by the Deep Fake Detection Challenge,of which 199 were made up and the remaining 53 were real.Ten seconds were allotted for each video.There were 318 videos used in all,199 of which were fake and 119 of which were real.Our proposedmethod achieved a testing accuracy of 91.47%,loss of 0.342,and AUC score of 0.92,outperforming two alternative approaches,CNN and MLP-CNN.Furthermore,our method succeeded in greater accuracy than contemporary models such as XceptionNet,Meso-4,EfficientNet-BO,MesoInception-4,VGG-16,and DST-Net.The novelty of this investigation is the development of a new Convolutional Neural Network(CNN)learning model that can accurately detect deep fake face photos.

Workout Action Recognition in Video Streams Using an Attention Driven Residual DC-GRU Network

Regular exercise is a crucial aspect of daily life, as it enables individuals to stay physically active, lowers thelikelihood of developing illnesses, and enhances life expectancy. The recognition of workout actions in videostreams holds significant importance in computer vision research, as it aims to enhance exercise adherence, enableinstant recognition, advance fitness tracking technologies, and optimize fitness routines. However, existing actiondatasets often lack diversity and specificity for workout actions, hindering the development of accurate recognitionmodels. To address this gap, the Workout Action Video dataset (WAVd) has been introduced as a significantcontribution. WAVd comprises a diverse collection of labeled workout action videos, meticulously curated toencompass various exercises performed by numerous individuals in different settings. This research proposes aninnovative framework based on the Attention driven Residual Deep Convolutional-Gated Recurrent Unit (ResDCGRU)network for workout action recognition in video streams. Unlike image-based action recognition, videoscontain spatio-temporal information, making the task more complex and challenging. While substantial progresshas been made in this area, challenges persist in detecting subtle and complex actions, handling occlusions,and managing the computational demands of deep learning approaches. The proposed ResDC-GRU Attentionmodel demonstrated exceptional classification performance with 95.81% accuracy in classifying workout actionvideos and also outperformed various state-of-the-art models. The method also yielded 81.6%, 97.2%, 95.6%, and93.2% accuracy on established benchmark datasets, namely HMDB51, Youtube Actions, UCF50, and UCF101,respectively, showcasing its superiority and robustness in action recognition. The findings suggest practicalimplications in real-world scenarios where precise video action recognition is paramount, addressing the persistingchallenges in the field. TheWAVd dataset serves as a catalyst for the development ofmore robust and effective fitnesstracking systems and ultimately promotes healthier lifestyles through improved exercise monitoring and analysis.