Search

An absorptive coding metasurface (ACM) is proposed to achieve radar cross section (RCS) reduction in this paper. In the design progress of the ACM, two different lossy coding elements are proposed at first, which can both be regarded as a composite composed of a two-layer resistive frequency selective surface (RFSS) and a polarization conversion metasurface (PCM). The two-layer RFSS has a certain wave-absorbing property due to ohmic loss. In addition, the PCM can achieve ultra-wideband linear polarization conversion, and the polarization-converted reflected waves in the two coding elements under the same incidence will differ by nearly 180° in phase because the sub-unit-cell structures in them are perpendicular to each other. Thus, based on the two lossy coding elements, the ACM is proposed, which can achieve ultra-wideband RCS reduction due to absorption and phase cancelation. Numerical simulations demonstrate that the RCS of the ACM under normal incidence can be reduced more than 10 dB in the ultra-wide frequency band from 6.9 to 41.2 GHz with a relative bandwidth of 142.6%. Moreover, it has the advantages of polarization-insensitivity and wide incident angle. Finally, one effective experimental verification is carried out, and a reasonable agreement is observed between the simulation and experimental results. [ABSTRACT FROM AUTHOR]

Summary: Delivering health care services in isolated rural regions through vehicular communications has recently attracted more attention. Real‐time video streaming is one of the most commonly used applications in such services. Escorting this increasing interest, there is a high demand for high‐quality streaming video in vehicular environments. However, these services face challenging network characteristics such as high dynamic topology and mobility, leading to high packet loss and degraded visual quality. This paper presents a smart approach to multi‐access terrestrial and non‐terrestrial networks (NTNs) for high‐quality and real‐time video streaming in vehicular environments to enhance healthcare services in remote areas. The proposed approach integrates a mobile telemedicine unit connected to an expert site through different channels, including satellite communication, 5 Generation (5G), and long‐term evolution (LTE) networks. A modified multipath QUIC extension (MPQUIC) was introduced to stream data hybridly through the network. Furthermore, multiple description coding (MDC) was applied to split data into two different descriptions and prioritize one over the other. Important data would be transmitted through cellular networks, and non‐priority data would be transmitted through satellite links, enhancing the reliability of video transmission. We demonstrate the effectiveness of our approach through the use of a connected ambulance as a case study. The Mininet‐Wifi was used to emulate network conditions. The peak signal‐to‐noise ratio (PSNR), structural SIMilarity (SSIM), and video multimethod assessment fusion (VMAF) were measured to evaluate the received video quality; the received data rate and packet loss were also calculated. The obtained results show our proposed method's efficiency by reducing latency by up to 60% and improving the receiving data rate by up to 143% compared with the classical MPQUIC. The proposed system enhances video quality by up to 70%. It minimizes packet loss by up to 50% compared with the unreliable QUIC, showcasing the potential to improve m‐health services' efficiency and mobility in isolated rural regions. [ABSTRACT FROM AUTHOR]

The quadtree partition process involves major complexity in high-efficiency video coding (HEVC/H.265). It divides the coding tree units (CTUs) recursively into coding units (CUs). Determining the coding unit partition depth based on rate-distortion optimisation is computationally difficult in HEVC. This article proposes a system based on a deep learning architecture for determining the coding unit partition depth with less time in HEVC intra-prediction. The proposed system minimises computing complexity by removing the rate-distortion optimisation. The proposed system comprises two main blocks: the pre-processing block and the deep learning block. During the pre-processing phase, the spatial resolution of the input data is drastically reduced, enabling the neural network model to quickly adapt to the input sample and extract more meaningful feature data. This paper proposes two distinct deep learning architectures, CU-VGG16 and CU-VGG19. Pre-processed coding units (16 × 16) are the input for the deep learning architecture, and the corresponding coding units' depths (0, 1, 2, 3) are the output. To compare the accuracy of coding unit depth prediction in the two proposed models, we have created a database with varying resolutions. The performance of the proposed models was observed by replacing the CU partition block of traditional HEVC with the proposed systems and comparing the bit rate and encoding time with traditional HEVC. The results demonstrated that the proposed architecture with CU-VGG16 and CU-VGG19 designs speeds up coding unit partitioning by 87.15% and 87.70%, respectively, as compared to standard HEVC. [ABSTRACT FROM AUTHOR]

The "Author Index Volume 18 (2024)" from the International Journal of Semantic Computing lists various authors and their respective articles published in the journal. Topics covered include AI ecosystems, video codecs, image classification, knowledge graphs, and robotic systems. The index provides a comprehensive overview of the research contributions in the field of semantic computing for the year 2024. [Extracted from the article]

Advancements in artificial intelligence have significantly increased the use of images and videos in machine analysis algorithms, predominantly neural networks. However, the traditional methods of compressing, storing and transmitting media have been optimized for human viewers rather than machines. Current research in coding images and videos for machine analysis has evolved in two distinct paths. The first is characterized by End-to-End (E2E) learned codes, which show promising results in image coding but have yet to match the performance of leading Conventional Video Codecs (CVC) and suffer from a lack of interoperability. The second path optimizes CVC, such as the Versatile Video Coding (VVC) standard, for machine-oriented reconstruction. Although CVC-based approaches enjoy widespread hardware and software compatibility and interoperability, they often fall short in machine task performance, especially at lower bitrates. This paper proposes a novel hybrid codec for machines named NN-VVC, which combines the advantages of an E2E-learned image codec and a CVC to achieve high performance in both image and video coding for machines. Our experiments show that the proposed system achieved up to − 43.20% and − 26.8% Bjøntegaard Delta rate reduction over VVC for image and video data, respectively, when evaluated on multiple different datasets and machine vision tasks according to the common test conditions designed by the VCM study group in MPEG standardization activities. Furthermore, to improve reconstruction quality, we introduce a human-focused branch into our codec, enhancing the visual appeal of reconstructions intended for human supervision of the machine-oriented main branch. [ABSTRACT FROM AUTHOR]

Video streaming systems aim to provide high-quality video adapted to clients' device and network conditions. For this purpose, adaptive streaming architectures encode video content at a variety of quality levels, organized in a bitrate ladder. However, compressing a video into multiple streams is resource-intensive, which may become especially problematic in live streaming applications with real-time demands. Therefore, this paper proposes a novel solution for fast bitrate ladder creation, and provides the requirements for implementation in the H.266/VVC standard. More specifically, the proposed method creates new intermediate combined streams by injecting the lowest temporal layers of a higher-quality augmentation stream in a lower-quality base stream. Since the lowest layers are used as reference by the remaining layers, this procedure indirectly increases the quality of the frames in those untouched remaining layers as well. Although altering the reference frames may cause some drift-error artifacts, we demonstrate that, on average, the quality of the intermediate streams are higher than the base stream. Additionally, we demonstrate that injecting more layers brings both the quality and bitrate closer to that of the augmentation stream. The disadvantage of the combined streams is that their quality fluctuates more than the quality of the source streams, and that they are compressed less efficiently, comparable to going from a slower to fast or faster preset in the VVenC encoder. Most importantly, their main advantage is that they were generated at no significant additional computational complexity. In this way, the proposed method is of great benefit when generating a bitrate ladder of video streams under constrained computational resources. The code has been made open source and is available on https://github.com/IDLabMedia/NALUProcessing. [ABSTRACT FROM AUTHOR]

In bearing fault diagnosis, traditional deep learning methods often fall short of achieving satisfactory diagnostic accuracy under variable operating conditions. A critical phase in this process is data acquisition, which heavily relies on high-precision sensors to accurately capture the real-time operational state of the bearing ring. To address this, a diversified sensor fusion strategy has been proposed, encompassing various sensor types such as temperature, and acoustic sensors. The strategy allows for comprehensive monitoring of the bearing's state from multiple dimensions. Vibration sensors are responsible for detecting minute vibrations and abnormal vibration patterns during the bearing's operation. Temperature sensors monitor changes in the bearing ring's temperature to identify potential overheating issues, whereas acoustic sensors capture unusual noises that may indicate faults. From the collective data gathered by these sensors, a comprehensive view of the bearing's operational state can be obtained, significantly enhancing the accuracy of fault diagnosis. To tackle the issue of low diagnostic accuracy under variable working conditions, an algorithm combining the advantages of data reconstruction and discriminative space optimization, data deconstruction and metalearning discriminative space optimization (DR-MLDSO), has been utilized. Additionally, by integrating a hybrid dual-channel attention mechanism into the feature extraction network, challenges arising from variable application scenarios and data quality issues have been effectively addressed. Faced with the challenge of insufficient sample size, a similarity-based meta-learning algorithm was employed to train the encoder. Furthermore, the introduction of new constraints in the loss function leads to an improved sparse denoising autoencoder that optimizes data reconstruction, effectively reducing noise while preserving key features. Finally, incorporating a self-attention mechanism enhances the model's diagnostic capabilities in noisy environments, achieving superior diagnostic performance under variable working conditions, even with small sample sizes. [ABSTRACT FROM AUTHOR]

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Identification of light sensitivities, manifesting either as hyper-sensitive (over-stimulating) or hypo-sensitive (under-stimulating) in children with autism spectrum disorder (ASD), is crucial for the development of personalized sensory environments and therapeutic strategies. Traditional methods for identifying light sensitivities often depend on subjective assessments and manual video coding methods, which are time-consuming, and very keen observations are required to capture the diverse sensory responses of children with ASD. This can lead to challenges for clinical practitioners in addressing individual sensory needs effectively. The primary objective of this work is to develop an automated system using Internet of Things (IoT), computer vision, and data mining techniques for assessing visual sensitivities specifically associated with light (color and illumination). For this purpose, an Internet of Things (IoT)-based light sensitivities assessing system (IoT-LSAS) was designed and developed using a visual stimulating device, a bubble tube (BT). The IoT-LSAS integrates various electronic modules for (i) generating colored visual stimuli with different illumination levels and (ii) capturing images to identify children's emotional responses during sensory stimulation sessions. The system is designed to operate in two different modes: a child control mode (CCM) and a system control mode (SCM). Each mode uses a distinct approach for assessing light sensitivities, where CCM uses a preference-based approach, and SCM uses an emotional response tracking approach. The system was tested on a sample of 20 children with ASD, and the results showed that the IoT-LSAS effectively identified light sensitivities, with a 95% agreement rate in the CCM and a 90% agreement rate in the SCM when compared to the practitioner's assessment report. These findings suggest that the IoT-LSAS can be used as an alternative to traditional assessment methods for diagnosing light sensitivities in children with ASD, significantly reducing the practitioner's time required for diagnosis. [ABSTRACT FROM AUTHOR]

Video coding has traditionally been developed to support services such as video streaming, videoconferencing, digital TV, and so on. The main intent was to enable human viewing of the encoded content. However, with the advances in deep neural networks (DNNs), encoded video is increasingly being used for automatic video analytics performed by machines. In applications such as automatic traffic monitoring, analytics such as vehicle detection, tracking and counting, would run continuously, while human viewing could be required occasionally to review potential incidents. To support such applications, a new paradigm for video coding is needed that will facilitate efficient representation and compression of video for both machine and human use in a scalable manner. In this manuscript, we introduce an end-to-end learnable video codec that supports a machine vision task in its base layer, while its enhancement layer, together with the base layer, supports input reconstruction for human viewing. The proposed system is constructed based on the concept of conditional coding to achieve better compression gains. Comprehensive experimental evaluations conducted on four standard video datasets demonstrate that our framework outperforms both state-of-the-art learned and conventional video codecs in its base layer, while maintaining comparable performance on the human vision task in its enhancement layer. [ABSTRACT FROM AUTHOR]

Summary: In this paper, a novel strategy of video communication over a 5G platform of new radio (NR) is developed, and it is named ViNR. With the support of optimization on the ViNR quality of service (QoS) system design, we stretched the outdated R‐D optimization to a novel delay‐distortion‐rate optimization (DDRO) control method. The entire model is partitioned with two types of coding: source coding and channel coding. For source coding, we affianced the inter‐frame prediction method of independent predicted frames (IPPPP) with Lagrange multiplier optimization. Channel coding is intricate with the minimization of delay‐distortion and getting the most out of the rate using resource allocation optimization in terms of sub‐slice allocation. To perform this sub‐slice resource assignment with optimization of DDR, the isolation resource allocation is premeditated in this work to ensure the service level profile of various groups of resource slots or grids dealing with the subject of middling delay and rate. The widespread simulation results divulge that the proposed algorithm NR‐DDRO achieves better QoS parameters of delay, distortion, and rate with the metrics of end‐to‐end distortion, encoding Y‐PSNR, encoding bit rate, encoding time, end‐to‐end PSNR, optimization time, and complete computation time. [ABSTRACT FROM AUTHOR]

The independent rate-distortion optimization technique for the video coding standard H. 266/VVC (versatile video coding) suffers from a loss in coding performance due to the oversight of temporal propagation effects of coding distortion in reference unit. To address this issue, this paper proposed a low-latency rate-distortion optimization algorithm based on the temporal influence of coding distortion. Firstly, leveraging the temporal propagation continuity characteristics of video images, it computed the temporal propagation influence weight of encoding distortion by considering motion compensation prediction errors and reconstruction errors. Secondly, it established a rate-distortion optimization model based on the temporal propagation impact of encoding distortion. Lastly, it utilized the temporal propagation influence weight of encoding distortion to adjust the Lagrange multipliers and quantization parameters of coding units. Experimental results demonstrate that, under low-delay P-frame and B-frame configurations, compared to the baseline algorithm, the BD-rate savings reach 1.6% and 0.9%, and the coding time decrease by 2.93% and 6.02%, respectively. The experimental results demonstrate that the algorithm proposed in this paper effectively improves coding performance without increasing encoding complexity, making it suitable for real-time encoding applications. [ABSTRACT FROM AUTHOR]

Drawing inspiration from the paradigm of engineering projects, this paper presents a novel real-time chaotic video encryption scheme based on multithreaded parallel computing and multiround confusion–diffusion architecture. It utilizes a contractor thread to retrieve and assign frames to worker threads, which operate concurrently to perform DNA coding, confusion, and diffusion operations on their designated frames for encryption, with the resulting frames processed by a dealer thread. To evaluate the performance of the proposed algorithm, it is implemented on a workstation equipped with an Intel Xeon Gold 6226 @ 2.9 GHz CPU and 64 GB of memory. The statistical and security analyses demonstrate that the proposed strategy exhibits exceptional statistical properties and provides robust resistance against various attacks. The encryption speed evaluations show that the deployed cryptosystem achieves delay-free 5 1 2 × 5 1 2  24 FPS video encryption, with an average encryption time of 34.69 ms, despite the execution of four rounds of DNA coding, five rounds of confusion, and three rounds of diffusion operations on each frame. In comparison to existing real-time chaotic video encryption schemes based on parallel computing, our method attains superior versatility and heightened security by processing each frame with an independent worker thread and incorporating DNA coding technology. [ABSTRACT FROM AUTHOR]

Video analytics can achieve increased speed and efficiency by operating directly on the compressed video format, thereby alleviating the decoding burden on the analytics server. The encoded video streams are rich in semantic binary information and this information can be utilized more efficiently to train the classifiers. Motivated by the same notion, a deep learning-based video compression-cum-classification network has been proposed. In the proposed work, the binary-coded semantic information is extracted by using an auto encoder-based video compression component and the same fed to the MobileNetv2-based classifier for the classification of the given video streams based on their content. Using large-scale user-generated content provided by YouTube UGC dataset, it has been demonstrated that using deep neural networks for compression not only provides on-par compression results to traditional methods, it makes analytical processing of these videos faster. Video content tagging of YouTube UGC dataset has been used as the analytics task. The proposed DLVCC approach performs 10 × faster with 30 × fewer parameters than MobileNetv2 in video tagging of compressed video with no loss in accuracy. [ABSTRACT FROM AUTHOR]

Introduction The use of tourniquets in combat medicine continues to be a key focus as they have consistently been shown to combat one of the leading causes of preventable death on the battlefield, massive hemorrhage to extremities. The present study analyzed tourniquet application among combat medics (68W) and combat lifesavers (CLSs) in a training environment to determine whether trainees' performance is consistent among one another and whether performance can be associated with participant demographics such as experience or role. Materials and Methods Study participants treated male and female patient simulators within a tactical field care phase, both of which experienced an amputated leg and required the application of a Combat Application Tourniquet (CAT). To assess tourniquet application variability and performance, a series of application subtasks and potential errors were measured via video coding of the scenarios by a team of 5 coders. Time to tourniquet application and tourniquet application duration were also coded to assess correlations between application duration and variability or performance. Results Results from analyzing tourniquet application subtasks and errors through a series of one-way ANOVA tests showed that application of the CAT first, hasty CAT application, and high tourniquet application were not predictive of participant role, time within the role, and self-reported tourniquet skill, confidence, or experience. Such demographic variables were also not predictive of successful tourniquet application as defined by the number of windlass rod rotations. Results from binomial logistic regressions showed that participant role and self-reported tourniquet skill and experience were predictors of tourniquet application duration. Conclusion The findings suggest that high variability in CAT application methodology and performance exists among CLS and combat medics, which is largely not predictable by various demographics such as role, experience within the designated role, and self-reported confidence, skill, or experience. The observed disconnect between training or experience and CAT application performance suggests substantial variability in the consistency of training for both CLS and 68W soldiers. These inconsistencies may stem from variability in instructor knowledge, teaching styles, or training materials or may be developed through informal methods such as experiences in the field or recommendations from colleagues and experts. These findings highlight a potential need to reassess CAT application training, particularly in regard to consistency and validation. Finally, it should be noted that the study's findings may be limited or fail to capture some study effects because of the sample size and wide range of reported experience among participants. [ABSTRACT FROM AUTHOR]

Recently, Arıkan proposed a polarization‐adjusted convolutional (PAC) codes, demonstrating their superior error correction performance over polar codes at short block lengths. It was confirmed that PAC codes approached the optimal performance achievable with limited code length. This paper proposes a novel low‐complexity list decoding algorithm for PAC codes, incorporating path splitting and pruning strategies based on a set of highly reliable information bits. Simulation results reveal that the proposed algorithm significantly reduces sorting complexity and average list size, all while incurring negligible performance loss. Unlike previous pruning algorithms designed for polar codes, the proposed strategy eliminates the need to individually assess the reliability of decoding paths in each decoding process. Instead, the algorithm minimizes redundant decoding paths through a high‐reliability information bit set, constructed using Monte Carlo experiments. [ABSTRACT FROM AUTHOR]

In the dynamic field of healthcare, clinical coding plays a key role in providing accurate and comprehensive information about patients' illnesses and their treatment as part of a comprehensive medical service. Coding systems are now part of health information systems across Europe. Much of what is known about the extent of prevalence, causes and consequences of human disease and mortality worldwide is based on the use of data coded according to the International Classification of Diseases (ICD). The ICD is the world's standard methodology for collecting mortality and morbidity data. The analysis of the available literature on the selected issues outlines the multidimensional role of coding systems in health care, which has a huge impact on decisionmaking in the process of providing medical services. In Bulgaria, despite the abundance of literary sources in the native medical literature, there is still a lack of a comprehensive analysis dedicated specifically to the importance of clinical coding. Regardless of what coding system in a country is used, it is important that medical institutions are trained and know how to record full and precise information about diagnoses and procedures. In this regard, a survey and analysis was conducted in various medical institutions within 6 months in 2023 among staff dealing with clinical coding in medical institutions: doctors, health care professionals, coders and others. The study focused on organization and training in clinical coding, with the aim of highlighting the key elements that contribute to the high degree of accuracy and efficiency in this important medical process. By analyzing the various aspects related to professionalism, training, and internal structures of medical institutions, the study seeks to reveal the inevitable relationship between well-organized and trained coding and increased quality of health care [ABSTRACT FROM AUTHOR]

Multimedia data (video, audio, images) require storage space and transmission bandwidth when sent through social media networking. Despite rapid advances in the capabilities of digital communication systems, the high data size and data transfer bandwidth continue to exceed the capabilities of available technology, especially among social media users. The recent growth of multimedia-based web applications such as WhatsApp, Telegram, and Messenger has created a need for more efficient ways to compress media data. This is because the transmission speed of networks for multimedia data is relatively slow. In addition, there is a specific size for sending files via email or social networks, because much high-definition multimedia information can reach the Giga Byte size. Moreover, most smart cameras have high imaging resolution, which increases the bit rate of multimedia files of video, audio, and image. Therefore, the goal of data compression is to represent media (video, audio, images, etc.) as accurately as possible with the minimum number of bits (bit rate). Traditional data compression methods are complex for users. They require a high processing power for media data. This shows that most of the existing algorithms have loss in data during the process of compressing and decompressing data, with a high bitrate for media data (video, audio, and image). Therefore, this work describes a new method for media compression systems by discrete Hartley matrix (128) to get a high speed and low bit rate for compressing multimedia data. Finally, the results show that the proposed algorithm has a high-performance speed with a low bit rate for compression data, without losing any part of data (video, sound, and image). Furthermore, the majority of users of social media are satisfied with the data compression interactive system, with high performance and effectiveness in compressing multimedia data. This, in turn, will make it easier for users to easily send their files of video, audio, and images via social media networks. [ABSTRACT FROM AUTHOR]

With the rapid development of multimedia services and smart devices, 360-degree video has enhanced the user viewing experience, ushering in a new era of immersive human–computer interaction. These technologies are increasingly integrating everyday life, including gaming, education, and healthcare. However, the uneven spatiotemporal distribution of wireless resources presents significant challenges for the transmission of ultra-high-definition 360-degree video streaming. To address this issue, this paper proposes a multi-layer non-uniform coding-based adaptive transmission method for 360° video (MNCATM). This method optimizes video caching and transmission by dividing non-uniform tiles and leveraging users' dynamic field of view (FoV) information and the multi-bitrate characteristics of video content. First, the video transmission process is formalized and modeled, and an adaptive transmission optimization framework for a non-uniform video is proposed. Based on this, the optimization problem required by the paper is summarized, and an algorithm is proposed to solve the problem. Simulation experiments demonstrate that the proposed method, MNCATM, outperforms existing transmission schemes in terms of bandwidth utilization and user quality of experience (QoE). MNCATM can effectively utilize network bandwidth, reduce latency, improve transmission efficiency, and maximize user experience quality. [ABSTRACT FROM AUTHOR]

Traditional image and video compression methods are designed to maintain the quality of human visual perception, which makes it necessary to reconstruct the image or video before machine analysis. Compression methods oriented towards machine vision tasks make it possible to use the bit stream directly for machine vision tasks, but it is difficult for them to decode high quality images. To bridge the gap between machine vision tasks and signal-level representation, researchers present plenty of the human-machine collaborative compression methods. In order to provide researchers with a comprehensive understanding of this field and promote the development of image and video compression, we present this survey. In this work, we give a problem definition and explore the relationship and application scenarios of different methods. In addition, we provide a comparative analysis of existing methods on compression and machine vision tasks performance. Finally, we provide a discussion of several directions that are most promising for future research. [ABSTRACT FROM AUTHOR]

Due to the limitations of current dynamic point cloud compression (DPCC) datasets, such as scarce categories, lack of detailed textures, and minimal variation in point cloud sequence movements. We present a comprehensive and diverse dataset, namely PKU-DPCC, to address the need for more categories and scene diversity for DPCC. Compared with the existing Moving Picture Experts Group (MPEG) and Audio Video Coding Standard (AVS) PCC datasets, the proposed dataset shows significant superiority in data scale, diversity, and compression difficulty. Specifically, our PKU-DPCC encompasses 50 dynamic point cloud sequences of six superclasses, and each sequence consists of 250 frames with geometry and attribute information and embodies the object or scene of a specific subclasses in the real world. Besides the diverse data content, samples in our dataset possess precise geometry details and various motion patterns, catering to a wide range of testing requirements in dynamic PCC. To construct this new dataset, we first collect numerous 3D meshes and then check the quality of each sample, resulting in 50 high-quality sequences for conversion to our final point cloud dataset. Furthermore, we conduct precise annotations for two scenarios of perceptible distortions and quality assessments on the provided point cloud data, which aims to broaden the range of its applications. To facilitate a fast algorithm performance evaluation, we select a part of representative samples constituting a subset, which has been adopted to the AVS PCC dataset. We conduct lossless and lossy compression tests on both geometry and attribute information from our subset to demonstrate the necessity of our newly constructed dataset. Experimental results reveal that the proposed dataset can become a new benchmark for evaluating and improving dynamic PCC algorithms. Our dataset is publicly available at https://openi.pcl.ac.cn/OpenDatasets/PKU-DPCC. [ABSTRACT FROM AUTHOR]

Versatile Video Coding (VVC) is a modern video compression standard designed to efficiently encode high definition video content, regardless of its diversity. It is expected to deliver superior compression performance compared to the previous standard, High Efficiency Video Coding (HEVC). However, the bit rate control problem for VVC can still be improved. To address this issue, a learning-based initial frame Quantization Parameter (QP) prediction algorithm has been proposed in this paper. This algorithm extracts information from image pixels and maps it to a feature matrix to reduce its additional cost. Furthermore, the problem of inaccurate determination of VVC QPs has been addressed by building a residual network to represent the frame complexity progressively and learning the optimal relationship between QPs and the target bit rate. Experimental results show that the proposed method reduces the control error from 10.74% to 7.19% compared to the original encoder. [ABSTRACT FROM AUTHOR]

Recently, human motion prediction has gained significant attention and achieved notable success. However, current methods primarily rely on training and testing with ideal datasets, overlooking the impact of variations in the viewing distance and viewing angle, which are commonly encountered in practical scenarios. In this study, we address the issue of model invariance by ensuring robust performance despite variations in view distances and angles. To achieve this, we employed Riemannian geometry methods to constrain the learning process of neural networks, enabling the prediction of invariances using a simple network. Furthermore, this enhances the application of motion prediction in various scenarios. Our framework uses Riemannian geometry to encode motion into a novel motion space to achieve prediction with an invariant viewing distance and angle using a simple network. Specifically, the specified path transport square-root velocity function is proposed to aid in removing the view-angle equivalence class and encode motion sequences into a flattened space. Motion coding by the geometry method linearizes the optimization problem in a non-flattened space and effectively extracts motion information, allowing the proposed method to achieve competitive performance using a simple network. Experimental results on Human 3.6M and CMU MoCap demonstrate that the proposed framework has competitive performance and invariance to the viewing distance and viewing angle. [ABSTRACT FROM AUTHOR]

Previous 2D video coding standards obtain efficient compression of traditional 2D color images. However, because new services, such as virtual reality (VR), augmented reality (AR), and mixed reality (MR), have been recently introduced, an immersive video coding standard that compresses view information captured at many viewpoints is being actively developed for high immersion of VR, AR, and MR. This video coding standard generates patches, which represent non-overlapping areas among different views. In general, the patches give a high impact on rendering of specular areas in virtual viewpoints, but it is very difficult to accurately find them. Therefore, this paper proposes an efficient immersive video coding method using specular detection for high rendering quality, which generates additional specular patches. Experimental results demonstrate that the proposed method improves the rendering quality in terms of specularity with a negligible change in coding performance. In particular, subjective assessments clearly show the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

3D-HEVC, which is a HEVC-compatible 3D video coding standard, was mainly developed to efficiently compress both a texture image and a depth map. Since the characteristics of the depth map are drastically different from those of the texture image, many advanced tools were adopted for depth intra coding in 3D-HEVC. In particular, a depth modelling mode (DMM) is evaluated to accurately predict sharp edges between objects. As a result, encoding complexity becomes very high. In order to reduce the high complexity, a fast depth intra mode decision method employing intra prediction cost and probability is proposed in this paper. Based on the cost and probability, the proposed method adaptively skips HEVC prediction modes and DMM in the mode decision. Experimental results demonstrate that it significantly reduces the encoding complexity, compared to conventional methods. [ABSTRACT FROM AUTHOR]

Virtual and augmented reality (VR/AR), teleoperation, and telepresence technologies heavily depend on video streaming and playback to enable immersive user experiences. However, the substantial bandwidth requirements and file sizes associated with VR/AR and 360-degree video content present significant challenges for efficient transmission and storage. Modern video coding standards, including HEVC, AV1, VP9, VVC, and EVC, have been designed to address these issues by enhancing coding efficiency while maintaining video quality on par with the H.264 standard. Nonetheless, the adaptive block structures inherent to these video coding standards introduce increased computational complexity, necessitating additional intra-prediction modes. The integration of AI in video coding has the potential to substantially improve video compression efficiency, reduce file sizes, and enhance video quality, making it a crucial area of research and development within the video coding domain. As AI systems can execute a wide array of tasks and adapt to new challenges, their incorporation into video coding may result in even more advanced compression techniques and innovative solutions to meet the ever-evolving demands of the industry. In this study, we introduce a state-of-the-art adaptive instant learning-based model, named iHELP, developed to address the computational complexity arising from encoders' adaptive block structures. The iHELP model achieves outstanding coding efficiency and quality while considerably improving encoding speed. iHELP model has been tested on HEVC, but it applies to other encoders with similar adaptive block structures. iHELP model employs entropy-based block similarity to predict the splitting decision of the LCU, determining whether to divide the block based on the correlation between the block content and previously adjacent encoded blocks in both spatial and temporal dimensions. Our methodology has been rigorously evaluated using the HEVC standard's common test conditions, and the results indicate that iHELP serves as an effective solution for efficient video coding in bandwidth-constrained situations, making it suitable for real-time video applications. The proposed method achieves an 80% reduction in encoding time while maintaining comparable PSNR performance relative to the RDO approach. The exceptional potential of the iHELP model calls for further exploration, as no other existing methods have demonstrated such a high level of performance. [ABSTRACT FROM AUTHOR]

As internet speeds increase and user demands for video quality grow, video coding standards continue to evolve. H.266/Versatile Video Coding (VVC), as the new generation of video coding standards, further improves compression efficiency but also brings higher computational complexity. Despite the significant advancements VVC has made in compression ratio and video quality, the introduction of new coding techniques and complex coding unit (CU) partitioning methods have also led to increased encoding complexity. This complexity not only extends encoding time but also increases hardware resource consumption, limiting the application of VVC in real-time video processing and low-power devices.To alleviate the encoding complexity of VVC, this paper puts forward a Bayesian and texture-feature-based fast splitting algorithm for coding intraframe bloc of VVC, which aims to reduce unnecessary computational steps, enhance encoding efficiency, and maintain video quality as much as possible. In the stage of rapid coding, the video frames are coded by the original VVC test model (VTM), and Joint Rough Mode Decision (JRMD) evaluation cost is used to update the parameter in the Bayesian algorithm to come and set the two thresholds to judge whether the current coding block continues to be split or not. Then, for coding blocks larger than those satisfying the above threshold conditions, the predominant direction of the texture within the coding block is ascertained by calculating the standard deviations along both the horizontal and vertical axes so as to skip some unnecessary splits in the current coding block patterns. The findings from our experiments demonstrate that our proposed approach improves the encoding rate by 1.40% on average, and the execution time of the encoder has been reduced by 49.50%. The overall algorithm has optimized the VVC intraframe coding technology and reduced the coding complexity of VVC. [ABSTRACT FROM AUTHOR]

The constant increase in multimedia Internet traffic in the form of video streaming requires new solutions for efficient video coding to save bandwidth and network resources. HTTP adaptive streaming (HAS), the most widely used solution for video streaming, allows the client to adaptively select the bitrate according to the transmission conditions. For this purpose, multiple presentations of the same video content are generated on the video server, which contains video sequences encoded at different bitrates with resolution adjustment to achieve the best Quality of Experience (QoE). This set of bitrate–resolution pairs is called a bitrate ladder. In addition to the traditional one-size-fits-all scheme for the bitrate ladder, context-aware solutions have recently been proposed that enable optimum bitrate–resolution pairs for video sequences of different complexity. However, these solutions use only spatial resolution for optimization, while the selection of the optimal combination of spatial and temporal resolution for a given bitrate has not been sufficiently investigated. This paper proposes bit-ladder optimization considering spatiotemporal features of video sequences and usage of optimal spatial and temporal resolution related to video content complexity. Optimization along two dimensions of resolution significantly increases the complexity of the problem and the approach of intensive encoding for all spatial and temporal resolutions in a wide range of bitrates, for each video sequence, is not feasible in real time. In order to reduce the level of complexity, we propose a data augmentation using a neural network (NN)-based model. To train the NN model, we used seven video sequences of different content complexity, encoded with the HEVC encoder at five different spatial resolutions (SR) up to 4K. Also, all video sequences were encoded using four frame rates up to 120 fps, presenting different temporal resolutions (TR). The Structural Similarity Index Measure (SSIM) is used as an objective video quality metric. After data augmentation, we propose NN models that estimate optimal TR and bitrate values as switching points to a higher SR. These results can be further used as input parameters for the bitrate ladder construction for video sequences of a certain complexity. [ABSTRACT FROM AUTHOR]

Predicting the consequences of the agent's actions on its environment is a pivotal challenge in robotic learning, which plays a key role in developing higher cognitive skills for intelligent robots. While current methods have predominantly relied on vision and motion data to generate the predicted videos, more comprehensive sensory perception is required for complex physical interactions such as contact-rich manipulation or highly dynamic tasks. In this work, we investigate the interdependence between vision and tactile sensation in the scenario of dynamic robotic interaction. A multi-modal fusion mechanism is introduced to the action-conditioned video prediction model to forecast future scenes, which enriches the single-modality prototype with a compressed latent representation of multiple sensory inputs. Additionally, to accomplish the interactive setting, we built a robotic interaction system that is equipped with both web cameras and vision-based tactile sensors to collect the dataset of vision-tactile sequences and the corresponding robot action data. Finally, through a series of qualitative and quantitative comparative study of different prediction architecture and tasks, we present insightful analysis of the cross-modality influence between vision, tactile and action, revealing the asymmetrical impact that exists between the sensations when contributing to interpreting the environment information. This opens possibilities for more adaptive and efficient robotic control in complex environments, with implications for dexterous manipulation and human-robot interaction. [ABSTRACT FROM AUTHOR]

As the performance of machine vision continues to improve, it is being used in various industrial fields to analyze and generate massive amounts of video data. Although the demand for and consumption of video data by machines has increased significantly, video coding for machines needs to be improved. It is therefore necessary to consider a new codec that differs from conventional codecs based on the human visual system (HVS). Spatial down-sampling plays a critical role in video coding for machines because it reduces the volume of the video data to be processed while maintaining the shape of the data's features that are important for the machine to reference when processing the video. An effective method of determining the intensity of spatial down-sampling as an efficient coding tool for machines is still in the early stages. Here, we propose a method of determining an optimal scale factor for spatial down-sampling by collecting and analyzing information on the number of objects and the ratio of the area occupied by the object within a picture. We compare the data reduction ratio to the machine accuracy error ratio (DRAER) to evaluate the performance of the proposed method. By applying the proposed method, the DRAER was found to be a maximum of 21.40 dB and a minimum of 11.94 dB. This shows that video coding gain for the machines could be achieved through the proposed method while maintaining the accuracy of machine vision tasks. [ABSTRACT FROM AUTHOR]

The purpose of this study was to examine the content of workout videos on TikTok. A sample of 297 TikTok workout videos was coded for demographic factors and body shape of content creators, as well as the presence of body positivity messaging, appearance-related messaging, and other relevant themes. The results suggest that TikTok workout content is often presented in a time-lapse format with little verbal instruction, which may make it difficult for viewers to perform the exercises. The majority of the videos depicted young women with athletic bodies and other characteristics associated with culturally based beauty ideals, and approximately half of the videos included non-White content creators. Approximately a quarter of the videos in the sample included objectification and a smaller proportion of the sample included messages about inner positivity. Overall, the TikTok platform may provide underrepresented individuals opportunities to seek out workout content from a more diverse group of instructors; however, the fact that many of these videos including objectifying depictions of the content creators is concerning. Further experimental work is needed in order to more fully elucidate the effects of TikTok workout videos on viewers. [ABSTRACT FROM AUTHOR]

Video compression remains a challenging task despite significant advancements in end-to-end optimized deep networks for video coding. This study, inspired by information bottleneck (IB) theory, introduces a novel approach that combines IB theory with wavelet transform. We perform a comprehensive analysis of information and mutual information across various mother wavelets and decomposition levels. Additionally, we replace the conventional average pooling layers with a discrete wavelet transform creating more advanced pooling methods to investigate their effects on information and mutual information. Our results demonstrate that the proposed model and training technique outperform existing state-of-the-art video compression methods, delivering competitive rate-distortion performance compared to the AVC/H.264 and HEVC/H.265 codecs. [ABSTRACT FROM AUTHOR]

The upcoming introduction of automated vehicles is expected to reduce the incidence of traffic accidents caused by human error. However, conditionally automated driving faces a significant challenge in that the driver must promptly take control when a request to intervene (RtI) is issued. Given this context, many studies have investigated the characteristics of the time it takes drivers to take control following an RtI and the factors influencing this time. It is also known that the driver's take-over response following an RtI is similar to the driver's braking response to the brake light of a lead vehicle or the yellow light of a traffic signal. Hence, findings on driver braking responses can provide valuable insights for take-over research. For example, gender was found to differentially affect perception time (PT) and movement time (MT), which are both subcomponents of the brake-response time in manual driving. Positive correlations were observed between these two times. These characteristics could be expected for PT and MT in take-over time (TOT) due to the similarities between braking and take-over responses; however, to the best of our knowledge, no study has yet examined these characteristics. Therefore, the present study was conducted to experimentally determine whether driver gender differentially affects the PT and MT, which are both subcomponents of TOT. Additionally, the correlations between these components were examined. This study provides novel insights into PT and MT during non-critical takeovers, facilitating a better understanding of TOT. Specifically, among drivers up to middle age, who were the target demographic group of this study, females tended to have a shorter PT, whereas males tended to have a shorter MT. This indicates that gender-specific approaches may be effective at reducing TOT, as gender is associated with differences in PT and MT. In addition, positive correlations were observed between PT, MT, and TOT. The correlation between PT and TOT indicates PT as an effective predictor of TOT. TOT data were collected in non-critical take-over scenarios, which are typical for conditionally automated vehicles. A total of 311 trials were performed using a driving simulator with 15 male and 15 female participants, resulting in 300 take-over data points. TOT was divided into PT and MT using video coding performed by two coders. Gender in this study was defined as being a biological male or female, and was obtained following the participants' permission. • Take-over time (TOT) was decomposed into perception time (PT) and movement time (MT). • Females tended to have a shorter PT, while males tended to have a shorter MT. • This tendency indicates that effective training to reduce TOT may differ by gender. • Positive correlations were found between PT, MT, and TOT. • The correlation between PT and TOT indicates that PT may be a predictor of TOT. [ABSTRACT FROM AUTHOR]

In the fifth generation (5G) new radio (NR) wireless communication system, using a multiple-input multiple-output (MIMO) system for signal transmission and reception of the millimeter wave frequency band can effectively improve data rate performance and received signal quality. Besides, precoding is an important method of beamforming in MIMO transmission. With the properly selected precoding matrices, the transmitter and receiver can adjust the transmitting and receiving behaviors in accordance with the changes of the current channel state to reduce the interferences between users and increase the received signal strength. In this paper, a low complexity precoding selection method is proposed based on the steering angle characteristics of the precoding matrices of 5G NR. In addition, for this paper, we used the software defined radio to implement the precoding selection following the requirement of the specifications of 5G. With this implementation, both the transmitter and receiver can determine the suitable precoding matrices according to different precoding selection methods. Results showed that with a little error vector magnitude performance degradation, the proposed precoding selection method can reduce at least 50% of the required computational complexity of the full search method. [ABSTRACT FROM AUTHOR]

The surge in ultra-high-definition video content has intensified the demand for advanced video compression techniques. Video encoding preprocessing can improve coding efficiency while ensuring a high degree of compatibility with existing codecs. Existing video encoding preprocessing methods are limited in their ability to fully exploit redundant features in video data and recover high-frequency details, and their network architectures often lack compatibility with neural video encoders. To addressing these challenges, we propose a Multi-Dimensional Enhancement and Reconstruction (MDER) preprocessing method to improve the efficiency of deep learning-based neural video encoders. Firstly, our approach integrates a degradation compensation module to mitigate encoding noise and boost feature extraction efficiency. Secondly, a lightweight fully convolutional neural network is employed, which utilizes residual learning and knowledge distillation to refine and suppress irrelevant features across spatial and channel dimensions. Furthermore, to maximize the use of redundant information, we incorporate Dense Blocks, which can enhance and reconstruct important features in the video data during preprocessing. Finally, the preprocessed frames are then mapped from pixel space to feature space through the Dense Feature-Enhanced Video Compression (DFVC) module, which improves motion estimation and compensation accuracy. The experimental results demonstrate that, compared to neural video encoders, the MDER method can reduce bits per pixel (Bpp) by 0.0714 and 0.0536 under equivalent PSNR and MS-SSIM conditions, respectively. These results demonstrate significant improvements in compression efficiency and reconstruction quality, highlighting the effectiveness of the MDER preprocessing method and its compatibility with neural video codec workflows. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Posts & Telecommunications (Natural Science Edition) is the property of Chongqing University of Posts & Telecommunications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The use of video streaming is constantly increasing. High-resolution video requires resources on both the sender and the receiver side. Many compression techniques can be utilized to compress the video and simultaneously maintain quality. The main goal of this paper is to provide an overview of video streaming and QoE. This paper describes the basic concepts and discusses existing methodologies to measure QoE. Subjective, objective, and video compression technologies are discussed. This review paper gathers the codec implementation developed by MPEG, Google, and Apple. This paper outlines the challenges and future research directions that should be considered in the measurement and assessment of the quality of experience for video services.

As the demand for higher quality 3D videos continues to grow, the 3D extensions of the Efficient Video Coding (3D-HEVC) standard are gradually unable to meet the needs of users. Versatile Video Coding Standard (H. 266/VVC), as an advanced video coding standard, adopts the nested Multi-Type Tree quadtree (QTMT) partitioning structure that current fast depth map coding unit (CU) partitioning methods cannot apply. Therefore, we have designed a fast intra-frame CU partitioning algorithm for VVC 3D video depth maps. Our proposed algorithm in this article consists of two steps, including two sub-algorithms. First, by analyzing the relationship between image entropy and variance and depth map CU division, we establish a bi-criterion decision algorithm to determine whether the texture complexity of the current CU is low enough to terminate its partitioning process. Then, for CUs that have been determined by the first algorithm to need further partitioning, we use a decision tree model based on Light Gradient Boosting Machine (LGBM) to predict which direction of Rate-Distortion Optimization (RDO) calculation can be skipped, which can avoid some unnecessary RDO calculations in a certain direction. The final experiment demonstrated the effect of the proposed algorithm, which can reduce 47.65% complexity of VVC 3D video intra-coding with negligible 0.23% Bjøntegaard Delta Bitrate (BDBR) increase, superior to other advanced methods. [ABSTRACT FROM AUTHOR]

In order to reduce the encoding complexity and stream size, improve the encoding performance and further improve the compression performance, the depth prediction partition encoding is studied in this paper. In terms of pattern selection strategy, optimization analysis is carried out based on fast strategic decision-making methods to ensure the comprehensiveness of data processing. In the design of adaptive strategies, different adaptive quantization parameter adjustment strategies are adopted for the equatorial and polar regions by considering the different levels of user attention in 360 degree virtual reality videos. The purpose is to achieve the optimal balance between distortion and stream size, thereby managing the output stream size while maintaining video quality. The results showed that this strategy achieved a maximum reduction of 2.92% in bit rate and an average reduction of 1.76%. The average coding time could be saved by 39.28%, and the average reconstruction quality was 0.043, with almost no quality loss detected by the audience. At the same time, the model demonstrated excellent performance in sequences of 4K, 6K, and 8K. The proposed deep partitioning adaptive strategy has significant improvements in video encoding quality and efficiency, which can improve encoding efficiency while ensuring video quality. [ABSTRACT FROM AUTHOR]

In the video compression industry, video compression tailored to machine vision tasks has recently emerged as a critical area of focus. Given the unique characteristics of machine vision, the current practice of directly employing conventional codecs reveals inefficiency, which requires compressing unnecessary regions. In this paper, we propose a framework that more aptly encodes video regions distinguished by machine vision to enhance coding efficiency. For that, the proposed framework consists of deep learning-based adaptive switch networks that guide the efficient coding tool for video encoding. Through the experiments, it is demonstrated that the proposed framework has superiority over the latest standardization project, video coding for machine benchmark, which achieves a Bjontegaard delta (BD)-rate gain of 5.91% on average and reaches up to a 19.51% BD-rate gain. [ABSTRACT FROM AUTHOR]

Video Coding for Machines (VCM) is gaining momentum in applications like autonomous driving, industry manufacturing, and surveillance, where the robustness of machine learning algorithms against coding artifacts is one of the key success factors. This work complements the MPEG/JVET standardization efforts in improving the resilience of deep neural network (DNN)-based machine models against such coding artifacts by proposing the following three advanced fine-tuning procedures for their training: (1) the progressive increase of the distortion strength as the training proceeds; (2) the incorporation of a regularization term in the original loss function to minimize the distance between predictions on compressed and original content; and (3) a joint training procedure that combines the proposed two approaches. These proposals were evaluated against a conventional fine-tuning anchor on two different machine tasks and datasets: image classification on ImageNet and semantic segmentation on Cityscapes. Our joint training procedure is shown to reduce the training time in both cases and still obtain a 2.4% coding gain in image classification and 7.4% in semantic segmentation, whereas a slight increase in training time can bring up to 9.4% better coding efficiency for the segmentation. All these coding gains are obtained without any additional inference or encoding time. As these advanced fine-tuning procedures are standard-compliant, they offer the potential to have a significant impact on visual coding for machine applications. [ABSTRACT FROM AUTHOR]

High Efficiency Video Coding (HEVC) offers superior compression rates, but its adoption introduces increased coding complexity due to its reliance on a recursive quad-tree for partitioning frames into varying block sizes. This quad-tree process is a central feature in upcoming video coding standards. Our paper presents a novel framework, SVG-CNN, which integrates three shallow Convolutional Neural Networks (CNNs) inspired by VGGNet. Each CNN is specifically designed for individual quad-tree levels to predict the Code Unit (CU) partition in HEVC, leading to reduced intra-frame coding time. SVG-CNN has an inherent capability for early terminations, leveraging sequential CNN feeding based on quad-tree level probabilities. This provides a mechanism to halt processes when further refinement is seemed unlikely. Enhancing the model's efficacy, we have crafted three specialized datasets, each focusing on distinct quad-tree levels and quantization parameter (QP) contexts. This allows each CNN within our framework to undergo targeted training, establishing a cutting-edge training methodology. Our study shows that performance, in terms of accuracy and F1 metrics, is highly dependent on QP settings, with lower QPs yielding better results, and higher QPs diminishing performance due to potential loss of critical features. To enhance our model, we tackled hyperparameter selection and CU split threshold determination for HEVC prediction. We utilized Grid Search Cross-Validation for the former and assessed multiple thresholds across selected videos for the latter. The model has a moderate complexity with over 328,000 parameters across 18 layers, which ensures memory efficiency. It boasts a swift prediction time of 0.05 ms and reduces HEVC encoding time by 61.64%, while slightly improving the bitrate-distortion performance by -0.24% BDBR, indicating better compression without notable PSNR loss. Significantly, our approach outperforms other CNN-based quad-tree partitioning methods that reduce HEVC coding complexity but sacrifice compression performance. [ABSTRACT FROM AUTHOR]

Over the past few years, there has been substantial interest and research activity surrounding the application of Convolutional Neural Networks (CNNs) for post-filtering in video coding. Most current research efforts have focused on using CNNs with various kernel sizes for post-filtering, primarily concentrating on High-Efficiency Video Coding/H.265 (HEVC) and Versatile Video Coding/H.266 (VVC). This narrow focus has limited the exploration and application of these techniques to other video coding standards such as AV1, developed by the Alliance for Open Media, which offers excellent compression efficiency, reducing bandwidth usage and improving video quality, making it highly attractive for modern streaming and media applications. This paper introduces a novel approach that extends beyond traditional CNN methods by integrating three different self-attention layers into the CNN framework. Applied to the AV1 codec, the proposed method significantly improves video quality by incorporating these distinct self-attention layers. This enhancement demonstrates the potential of self-attention mechanisms to revolutionize post-filtering techniques in video coding beyond the limitations of convolution-based methods. The experimental results show that the proposed network achieves an average BD-rate reduction of 10.40% for the Luma component and 19.22% and 16.52% for the Chroma components compared to the AV1 anchor. Visual quality assessments further validated the effectiveness of our approach, showcasing substantial artifact reduction and detail enhancement in videos. [ABSTRACT FROM AUTHOR]

Multi-object tracking tasks aim to assign unique trajectory codes to targets in video frames. Most detection-based tracking methods use Kalman filtering algorithms for trajectory prediction, directly utilizing associated target features for trajectory updates. However, this approach often fails, with camera jitter and transient target loss in real-world scenarios. This paper rethinks state prediction and fusion based on target temporal features to address these issues and proposes the SimpleTrackV2 algorithm, building on the previously designed SimpleTrack. Firstly, to address the poor prediction performance of linear motion models in complex scenes, we designed a target state prediction algorithm called LSTM-MP, based on long short-term memory (LSTM). This algorithm encodes the target's historical motion information using LSTM and decodes it with a multilayer perceptron (MLP) to achieve target state prediction. Secondly, to mitigate the effect of occlusion on target state saliency, we designed a spatiotemporal attention-based target appearance feature fusion (TSA-FF) target state fusion algorithm based on the attention mechanism. TSA-FF calculates adaptive fusion coefficients to enhance target state fusion, thereby improving the accuracy of subsequent data association. To demonstrate the effectiveness of the proposed method, we compared SimpleTrackV2 with the baseline model SimpleTrack on the MOT17 dataset. We also conducted ablation experiments on TSA-FF and LSTM-MP for SimpleTrackV2, exploring the optimal number of fusion frames and the impact of different loss functions on model performance. The experimental results show that SimpleTrackV2 handles camera jitter and target occlusion better, achieving improvements of 1.6%, 3.2%, and 6.1% in MOTA, IDF1, and HOTA, respectively, compared to the SimpleTrack algorithm. [ABSTRACT FROM AUTHOR]

Advanced video codecs such as High Efficiency Video Coding/H.265 (HEVC) and Versatile Video Coding/H.266 (VVC) are vital for streaming high-quality online video content, as they compress and transmit data efficiently. However, these codecs can occasionally degrade video quality by adding undesirable artifacts such as blockiness, blurriness, and ringing, which can detract from the viewer's experience. To ensure a seamless and engaging video experience, it is essential to remove these artifacts, which improves viewer comfort and engagement. In this paper, we propose a deep feature fusion based convolutional neural network (CNN) architecture (VVC-PPFF) for post-processing approach to further enhance the performance of VVC. The proposed network, VVC-PPFF, harnesses the power of CNNs to enhance decoded frames, significantly improving the coding efficiency of the state-of-the-art VVC video coding standard. By combining deep features from early and later convolution layers, the network learns to extract both low-level and high-level features, resulting in more generalized outputs that adapt to different quantization parameter (QP) values. The proposed VVC-PPFF network achieves outstanding performance, with Bjøntegaard Delta Rate (BD-Rate) improvements of 5.81% and 6.98% for luma components in random access (RA) and low-delay (LD) configurations, respectively, while also boosting peak signal-to-noise ratio (PSNR). [ABSTRACT FROM AUTHOR]

Image compression is a widely used technique to reduce the spatial redundancy in images. Recently, learning based image compression has achieved significant progress by using the powerful representation ability from neural networks. However, the current learning based image compression methods suffer from the huge computational cost, which limits their capacity for practical applications. In this paper, we propose a unified framework called Efficient Deep Image Compression (EDIC) based on three new technologies, including a channel attention module, a Gaussian mixture model and a decoder-side enhancement module. Specifically, we design an auto-encoder style network for learning based image compression. To improve the coding efficiency, we exploit the channel relationship between latent representations by using the channel attention module. Besides, the Gaussian mixture model is introduced for the entropy model and improves the accuracy for bitrate estimation. Furthermore, we introduce the decoder-side enhancement module to further improve image compression performance. Our EDIC method can also be readily incorporated with the Deep Video Compression (DVC) framework (Lu et al. 2019) to further improve the video compression performance. Simultaneously, our EDIC method boosts the coding performance significantly while bringing slightly increased computational cost. More importantly, experimental results demonstrate that the proposed approach outperforms the current image compression methods and is up to more than 150 times faster in terms of decoding speed when compared with Minnen's method (Minnen et al. 2018). Moreover, we also evaluate the performance of the human-centric task (i.e., face recognition) by using different coding strategies. [ABSTRACT FROM AUTHOR]

Link prediction has a wide range of applications in the study of complex networks, and the current research on link prediction based on single-layer networks has achieved fruitful results, while link prediction methods for multilayer networks have to be further developed. Existing research on link prediction for multilayer networks mainly focuses on multiplexed networks with homogeneous nodes and heterogeneous edges, while there are relatively few studies on general multilayer networks with heterogeneous nodes and edges. In this context, this paper proposes a method for heterogeneous multilayer networks based on motifs for link prediction. The method considers not only the effect of heterogeneity of edges on network links but also the effect of heterogeneous and homogeneous nodes on the existence of links between nodes. In addition, we use the role function of nodes to measure the contribution of nodes to form the motifs with links in different layers of the network, thus enabling the prediction of intra- and inter-layer links on heterogeneous multilayer networks. Finally, we apply the method to several empirical networks and find that our method has better link prediction performance than several other link prediction methods on multilayer networks. [ABSTRACT FROM AUTHOR]

Panoramic video multimedia technology has made significant advancements in recent years, providing users with an immersive experience by displaying the entire 360° spherical scene centered around their virtual location. However, due to its larger data volume compared to traditional video formats, transmitting high-quality videos requires more bandwidth. It is important to note that users do not see the whole 360° content simultaneously, but only a portion that is within their viewport. To save bandwidth, viewport-based adaptive streaming has become a significant technology that transmits only the viewports of interest to the user in high quality. Therefore, the accuracy of viewport prediction plays a crucial role. However, the performance of viewport prediction is affected by the size of the prediction window, which decreases significantly as the window size increases. In order to address this issue, we propose an effective self-attention viewport prediction model based on distance constraint in this paper. Firstly, by analyzing the existing viewport trajectory dataset, we find the randomness and continuity of the viewport trajectory. Secondly, to solve the randomness problem, we design a viewport prediction model based on a self-attention mechanism to provide more trajectory information for long inputs. Thirdly, in order to ensure the continuity of the predicted viewport trajectory, the loss function is modified with the distance constraint to reduce the change in the continuity of prediction results. Finally, the experimental results based on the real viewport trajectory datasets show that the algorithm we propose has higher prediction accuracy and stability compared with the advanced models. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Beijing University of Technology is the property of Journal of Beijing University of Technology, Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)