Video Quality Research Articles

Educational quality of Robotic Whipple videos on YouTube

BackgroundVideos on Robotic pancreaticoduodenectomy (RPD) may be watched by surgeons learning RPD. This study sought to appraise the educational quality of RPD videos on YouTube. MethodsOne hundred videos showing RPD or ‘Robotic Whipple’ were assessed using validated scales (LAP-VEGaS & Consensus Statement Score (CSS)). The association between the scores and characteristics of the video (e.g. order of appearance, provider type, etc.) was assessed. The minimum number of videos required to cumulatively cover the entire LAP-VEGaS and CSS was also noted. ResultsThe videos were of variable quality; median LAP-VEGaS = 0.67 (0.17–0.94), median CSS = 0.45 (0.29–0.53). There was no association between the educational quality of the videos and their order of appearance, view counts, provider type, length or country of origin. Videos lacked information such as patient consent (100%), potential pitfalls (97%) or surgeon credentials (84%). The first 29 videos cumulatively met all the criteria of CSS and LAP-VEGaS scores except for reporting consent. ConclusionYouTube videos on RPD are of variable quality, without any recognised predictors of quality, and miss important safety information. An impractical number of videos need to be watched to cumulatively fulfil educational criteria. There is a need for high-quality, peer-reviewed videos that adhere to educational principles.

DMUST360: Distortion‐aware multicast‐unicast superposed transmission for multiuser 360‐degree video

Abstract360‐degree video has gained popularity since it is associated with immersive user experience of virtual reality content. However, providing high‐quality 360‐degree video for a large number of users is difficult, especially in limited bandwidth conditions. Nonorthogonal multiple access technology‐enabled multicast offers a possible solution, but it also introduces some challenges, including in terms of satisfying users' individual requirements, ensuring video quality and so forth. In order to address these issues, we introduce a novel distortion‐aware multicast‐unicast superposed transmission scheme for multiuser 360‐degree video, which combines the advantages of multicast, unicast, and nonorthogonal multiple access technologies with consideration of the field of view of multiple users. To improve video quality, a distortion minimization problem is formulated. Based on matching theory, we proposed a multicast‐unicast coalition game algorithm to solve the problem efficiently. A series of trace‐driven simulations are carried out, which have shown the effectiveness of the proposed solution in terms of video quality and throughput.

Complementary and Alternative Medicine for Hidradenitis Suppurativa Discussed on TikTok: A Cross-Sectional Analysis.

Hidradenitis suppurativa (HS) is a painful, chronic inflammatory skin disease that negatively affects patient quality of life, and conventional treatments are variably effective. As a result, patients often turn to complementary and alternative medicine (CAM) for pain relief. Social media enables HS patients to share treatment recommendations. TikTok is a popular social media platform, but little is known about the HS treatments discussed in TikTok videos.  Objective: To evaluate the content and quality of information on TikTok regarding CAM HS therapies.  Methods: A cross-sectional analysis was conducted by performing a search in TikTok using the terms #hidradenitissuppurativa, #hswarrior, #naturalremedy, #complementarymedicine, #alternativemedicine, and #HStreatment. Two independent reviewers evaluated video quality using the DISCERN and AVA instruments. Linear regressions compared the engagement, DISCERN, and AVA scores among different uploader types. In total, 91 TikTok videos were analyzed. Videos were uploaded by non-physicians (82.4), dermatologists (6.6%), and private companies (11.0%). The average DISCERN and AVA scores were 36.2 and 1.6, respectively (poor quality). Common CAM therapies were natural salves, turmeric, Epsom salts, elimination diets, and zinc supplements. Physician-uploaded videos were of significantly higher quality than videos by other uploader types, with an average DISCERN and AVA score of 44.3 (P<0.009) and 2.6 (P<0.001), respectively (fair quality). TikTok videos were poor quality (low DISCERN and AVA scores); physician-uploaded videos were fair quality. Dermatologists can improve video quality by adequately discussing the supporting evidence, mechanisms of action, and remaining questions for HS treatments.  J Drugs Dermatol. 2024;23(3):e93-96. doi:10.36849/JDD.7738e.

Eating skills in children with autism via video modeling: an evaluation of face and content validation

<p>Children with autism spectrum disorder (ASD) may have their eating habits impacted by their traits, such as difficulty remaining seated at the table and exhibiting behaviors during mealtime. This often worries parents and causes stress and anxiety. Given video modeling's potential in helping children with ASD, experts should evaluate its effectiveness for teaching eating skills due to limited research in this area. Thus, the study aim to evaluate the validity of the developed videos of eating skills for children with ASD. For face validity, a focus group discussion was held to obtain experts' feedback on the eating skills video and was transcribed verbatim. Otherwise for content validity, the experts received content validity assessment forms and guidelines via email and the results was analysed using Microsoft excell. Face validity revealed four themes: suitability of videos, video quality and clarity, video instructions suitability, task analysis arrangement, and "other" recommendations. On the other hand, Video 1 and Video 2 scored 0.93 for relevance, clarity, simplicity, and ambiguity for the S-CVI/Ave (scale-level content validity index based on the average method) which was considered acceptable. Video 3 received a satisfactory S-CVI/Ave score of 0.93 for relevance, simplicity, and ambiguity, but its clarity score at 0.91, and still within an acceptable range, though not particularly high. As a conclusion, all task analyses for the videos met the requirement to be considered acceptable. Addressing the suggestions for improvement can increase the video's efficacy in teaching eating skills and relieving parents' concerns.</p>

Meniscus-Related Videos on TikTok Are Widely Viewed and Shared but the Educational Quality for Patients Is Poor

PurposeTo evaluate the quality of meniscus-related TikTok videos to better understand their value for patient education. MethodsThe term “meniscus” was used as the keyword for an extensive online search of video content on the TikTok on November 14, 2023. The first 100 videos were used for analysis. The duration of the videos, and the number of likes, shares and views were recorded for each video. Furthermore, videos were categorized based on the source (health workers, private user), the type of subject (patient experience, physcal therapy, anatomy, clinical examnation, surgical technique and injury mechanism), type of content (patient experience/testimony, education, rehabilitation) and the presence of music or voice. The quality and reliability assessments of video contents were conducted using the DISCERN instrument, the Journal of the American Medical Association (JAMA) benchmark criteria, and Global Quality Score (GQS). ResultsOf the 100 videos included in this study, 62 (62.0%) videos were published by health workers, 38 by private users (38.0%). Most of the information regarded patient experience (36–36.0%), followed by physical therapy (32–32.0%), anatomy (14–14.0%), clinical examination (8–8.0%), surgical technique (6–6.0%), and injury mechanism (4–4.0%). Video content reported patient experience in 39 (39.0%) videos, rehabilitation in 31 (31.0%) videos, and education in the remaining 30 (30.0%). The mean length of the videos was 39.12±49.56 seconds. The mean number of views was 1383001.65±5291822.28, while the mean numbers of comments, likes and shares were 408.53±1976.90, 54763.43±211823.44 and 873.70±2802.01, respectively. The mean DISCERN score, JAMA score and GQS were 17.93±5.07, 0.24±0.47 and 1.15±0.41, respectively. ConclusionsMeniscus-related videos on TikTok are widely viewed and shared, but the overall educational value to patients was poor.

Video games and disability-a risk and benefit analysis.

Over the past decades, video games have become a substantial part of the entertainment industry. While ubiquitous, video game participation remains low among people with disabilities amid potential negative effects. This article analyzes the risks and benefits that video games may present to individuals with disabilities. In this conceptual article, we explored the literature pertaining to video games and disability. To better understand the impact of video games on individuals with disabilities, we focused on the unique features of video games through the lens of the Self-Determination Theory. Our findings show that individuals with disabilities are most at risk from excessive video game use, leading to increased aggression, sedentary behavior, and negative impact on academic performance. Identified benefits include promoting physical rehabilitation and psychological well-being, improving cognitive abilities and emotional regulation, and utility in promoting exercises, and managing chronic pain. This article presents a number of strategies and resources to help guide individuals with disabilities, educators, practitioners, and researchers in maximizing the benefits of video games while controlling the risks.

End-to-End Transformer for Compressed Video Quality Enhancement

End-to-End Transformer for Compressed Video Quality Enhancement

MagView++: Data Exfiltration via CPU Magnetic Signals Under Video Decoding

Air-gapped networks achieve security by using physical isolation to keep the computers and network from the Internet. However, magnetic covert channels based on CPU utilization have been proposed to help secret data to exfiltrate from the Faraday-cage and the air gap. Despite the success of such covert channels, they suffer from the high risk of being detected by the transmitter computer and the challenge of installing malware into such a computer. In this paper, we propose <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MagView++</monospace> , where sensitive information is embedded in other data such as video and can be transmitted over the internal network. When any computer uses the data such as playing the video, the sensitive information will leak through the magnetic signals. The “separation” of information embedding and leaking, combined with the fact that the data can be exfiltrated from any computer in a distributed manner, overcomes these limitations. We demonstrate that CPU utilization for video decoding can be effectively controlled by changing the video frame type, reducing the quantization parameter, and changing the timestamp of the frame, without video quality degradation. We prototype <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MagView++</monospace> and achieve 8.9 bps throughput with 0.0057 BER when using a smartphone as the receiver, and 59 bps throughput with 0.0025 BER when using a dedicated devices with high sampling rate as the receiver. Experiments under various environments are conducted to show the robustness of <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MagView++</monospace> . Limitations and possible countermeasures are also discussed.

Omnidirectional Video Quality Assessment With Causal Intervention

Omnidirectional Video Quality Assessment With Causal Intervention

Multi-Modal Learning-Based Blind Video Quality Assessment Metric for Synthesized Views

Multi-Modal Learning-Based Blind Video Quality Assessment Metric for Synthesized Views

Edge-Enhanced TempoFuseNet: A Two-Stream Framework for Intelligent Multiclass Video Anomaly Recognition in 5G and IoT Environments

Surveillance video analytics encounters unprecedented challenges in 5G and IoT environments, including complex intra-class variations, short-term and long-term temporal dynamics, and variable video quality. This study introduces Edge-Enhanced TempoFuseNet, a cutting-edge framework that strategically reduces spatial resolution to allow the processing of low-resolution images. A dual upscaling methodology based on bicubic interpolation and an encoder–bank–decoder configuration is used for anomaly classification. The two-stream architecture combines the power of a pre-trained Convolutional Neural Network (CNN) for spatial feature extraction from RGB imagery in the spatial stream, while the temporal stream focuses on learning short-term temporal characteristics, reducing the computational burden of optical flow. To analyze long-term temporal patterns, the extracted features from both streams are combined and routed through a Gated Recurrent Unit (GRU) layer. The proposed framework (TempoFuseNet) outperforms the encoder–bank–decoder model in terms of performance metrics, achieving a multiclass macro average accuracy of 92.28%, an F1-score of 69.29%, and a false positive rate of 4.41%. This study presents a significant advancement in the field of video anomaly recognition and provides a comprehensive solution to the complex challenges posed by real-world surveillance scenarios in the context of 5G and IoT.

Video quality adaptation using CNN and RNN models for cost-effective and scalable video streaming Services

AbstractVideo streaming services require adaptive bit rate strategies that optimize video quality based on network conditions and user preferences to provide a cost-effective and scalable solution. In this manuscript, we present a novel architecture that utilizes a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to extract features from the video stream and predict optimal bit rates for each frame. The CNN feature extractor extracts relevant features from the input video stream, which are then passed on to the RNN predictor, where the optimal bit rate is predicted to ensure a personalized viewing experience tailored to the current network conditions and specific user preferences. Our experimental results demonstrate that the proposed architecture achieves significant improvements in video quality while minimizing bandwidth usage and providing a better user experience. Specifically, our results show a 37.1% improvement in average bit rate, indicating that the proposed architecture optimizes the video quality and reduces bandwidth usage by 37.1% on average. We also observed a 16.6% improvement in Quality of Experience (QoE), meaning that users will perceive the video quality as better. Additionally, rebuffering was reduced by 87.5%, indicating that users enjoy smoother video playback without interruptions. Importantly, our architecture is optimized for Dynamic Adaptive Streaming over HTTP (DASH), addressing the need for efficient streaming over the most widely used protocol in the industry.

Cross-lingual few-shot sign language recognition

There are over 150 sign languages worldwide, each with numerous local variants and thousands of signs. However, collecting annotated data for each sign language to train a model is a laborious and expert-dependent task. To address this issue, this paper introduces the problem of few-shot sign language recognition (FSSLR) in a cross-lingual setting. The central motivation is to be able to recognize a novel sign, even if it belongs to a sign language unseen during training, based on a small set of examples. To tackle this problem, we propose a novel embedding-based framework that first extracts a spatio-temporal visual representation based on video and hand features, as well as hand landmark estimates. To establish a comprehensive test bed, we propose three meta-learning FSSLR benchmarks that span multiple languages, and extensively evaluate the proposed framework. The experimental results demonstrate the effectiveness and superiority of the proposed approach for few-shot sign language recognition in both monolingual and cross-lingual settings.

Throughput Prediction of 5G Network Based on Trace Similarity for Adaptive Video

Predicting throughput is essential to reduce latency in time-critical services like video streaming, which constitutes a significant portion of mobile network traffic. The video player continuously monitors network throughput during playback and adjusts the video quality according to the network conditions. This means that the quality of the video depends on the player’s ability to predict network throughput accurately, which can be challenging in the unpredictable environment of mobile networks. To improve the prediction accuracy, we grouped the throughput trace into clusters taking into account the similarity of their mean and variance. Once we distinguished the similar trace fragments, we built a separate LSTM predictive model for each cluster. For the experiment, we used traffic captured from 5G networks generated by individual user equipment (UE) in fixed and mobile scenarios. Our results show that the prior grouping of the network traces improved the prediction compared to the global model operating on the whole trace.

Effects of Browsing Conditions and Visual Alert Design on Human Susceptibility to Deepfakes

The increasing reach of deepfakes raises practical questions about people’s ability to detect false videos online. How vulnerable are people to deepfake videos? What technologies can help improve detection? Previous experiments that measure human deepfake detection historically omit a number of conditions that can exist in typical browsing conditions. Here, we operationalized four such conditions (low prevalence, brief presentation, low video quality, and divided attention), and found in a series of online experiments that all conditions lowered detection relative to baseline, suggesting that the current literature underestimates people’s susceptibility to deepfakes. Next, we examined how AI assistance could be integrated into the human decision process. We found that a model that exposes deepfakes by amplifying artifacts increases detection rates, and also leads to higher rates of incorporating AI feedback and higher final confidence than text-based prompts. Overall, this suggests that visual indicators that cause distortions on fake videos may be effective at mitigating the impact of falsified video.

Two-path target-aware contrastive regression for action quality assessment

Action quality assessment (AQA) is a challenging vision task due to the complexity and variance of the scoring rules embedded in the videos. Recent approaches have reduced the prediction difficulty of AQA via learning action differences between videos, but there are still challenges in learning scoring rules and capturing feature differences. To address these challenges, we propose a two-path target-aware contrastive regression (T2CR) framework. We propose to fuse direct and contrastive regression and exploit the consistency of information across multiple visual fields. Specifically, we first directly learn the relational mapping between global video features and scoring rules, which builds occupational domain prior knowledge to better capture local differences between videos. Then, we acquire the auxiliary visual fields of the videos through sparse sampling to learn the commonality of feature representations in multiple visual fields and eliminate the effect of subjective noise from a single visual field. To demonstrate the effectiveness of T2CR, we conduct extensive experiments on four AQA datasets (MTL-AQA, FineDiving, AQA-7, JIGSAWS). Our method is superior to state-of-the-art methods without elaborate structural design and fine-grained information.

Cross-Modality Interaction-Based Traffic Accident Classification

Traffic accidents on the road lead to serious personal and material damage. Furthermore, preventing secondary accidents caused by traffic accidents is crucial. As various technologies for detecting traffic accidents in videos using deep learning are being researched, this paper proposes a method to classify accident videos based on a video highlight detection network. To utilize video highlight detection for traffic accident classification, we generate information using the existing traffic accident videos. Moreover, we introduce the Car Crash Highlights Dataset (CCHD). This dataset contains a variety of weather conditions, such as snow, rain, and clear skies, as well as multiple types of traffic accidents. We compare and analyze the performance of various video highlight detection networks in traffic accident detection, thereby presenting an efficient video feature extraction method according to the accident and the optimal video highlight detection network. For the first time, we have applied video highlight detection networks to the task of traffic accident classification. In the task, the most superior video highlight detection network achieves a classification performance of up to 79.26% when using video, audio, and text as inputs, compared to using video and text alone. Moreover, we elaborated the analysis of our approach in the aspects of cross-modality interaction, self-attention and cross-attention, feature extraction, and negative loss.

Suboptimal video coding for machines method based on selective activation of in‐loop filter

AbstractA conventional codec aims to increase the compression efficiency for transmission and storage while maintaining video quality. However, as the number of platforms using machine vision rapidly increases, a codec that increases the compression efficiency and maintains the accuracy of machine vision tasks must be devised. Hence, the Moving Picture Experts Group created a standardization process for video coding for machines (VCM) to reduce bitrates while maintaining the accuracy of machine vision tasks. In particular, in‐loop filters have been developed for improving the subjective quality and machine vision task accuracy. However, the high computational complexity of in‐loop filters limits the development of a high‐performance VCM architecture. We analyze the effect of an in‐loop filter on the VCM performance and propose a suboptimal VCM method based on the selective activation of in‐loop filters. The proposed method reduces the computation time for video coding by approximately 5% when using the enhanced compression model and 2% when employing a Versatile Video Coding test model while maintaining the machine vision accuracy and compression efficiency of the VCM architecture.

Video stabilization based on low‐rank constraint and trajectory optimization

AbstractVideo stabilization plays a pivotal role in enhancing video quality by eliminating unwanted jitter in shaky videos. This paper introduces a novel video stabilization algorithm that leverages low‐rank constraint and trajectory optimization to effectively eliminate undesirable motion and generate stabilized videos. In the proposed algorithm, a low‐rank constraint regularization term is incorporated to enhance the smoothness of motion trajectories. Additionally, a predictive path smoothness term is integrated to ensure the consistency of motion across neighbouring frames. To address the problem of excessive cropping resulting from aggressive smoothing, a flexible local window strategy that emphasizes local motion relationships within the trajectories is introduced. The experimental results show that, compared to other excellent video stabilization algorithms, the proposed algorithm improves the stability metric by approximately 2.3%. Furthermore, in the stabilized videos generated by the algorithm, an approximate improvement of 2.18 dB in average image temporal fidelity and a 5.7% increase in average structural similarity between adjacent frames are achieved. The code that implements the proposed method is publicly accessible at https://github.com/CZS0319/VS_Low‐Rank_Constraint_Trajectory_Optimization.

Action Segmentation Through Self-Supervised Video Features and Positional-Encoded Embeddings

Action segmentation consists of temporally segmenting a video and labeling each segmented interval with a specific action label. In this work, we propose a novel action segmentation method that requires no initial video analysis and no annotated data. Our proposal involves extracting features from videos using several pre-trained deep-learning models, including spatiotemporal and self-supervised methods. Data is then transformed using a positional encoder, and finally, a clustering algorithm is applied, where each produced cluster presumably corresponds to a different single and distinguishable action. For self-supervised features, we explored DINO, and for spatiotemporal features, we investigated I3D and SlowFast methods. Moreover, two different clustering algorithms (FINCH and KMeans) were investigated, and we also explored how varying the length of video snippets that generate the feature vectors affected the quality of the segmentation. Experiments show that our method produces competitive results on the Breakfast and INRIA Instructional Videos dataset benchmarks. Our best result was produced using a composition of self-supervised features generated by DINO, FINCH clustering, and positional encoding.