Pub Date : 2023-01-05DOI: 10.1109/mmul.2022.3222919
Presents information about the content of the publication.
表示有关出版物内容的信息。
{"title":"Computing in Science & Engineering","authors":"","doi":"10.1109/mmul.2022.3222919","DOIUrl":"https://doi.org/10.1109/mmul.2022.3222919","url":null,"abstract":"Presents information about the content of the publication.","PeriodicalId":13240,"journal":{"name":"IEEE MultiMedia","volume":"19 3-4","pages":""},"PeriodicalIF":3.2,"publicationDate":"2023-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138513837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.1109/mmul.2023.3326835
Ming-Hung Wang, Ting-Shen Hsieh, Yu-Yao Tseng, Po-Wen Chi
This paper introduces a novel framework designed to enhance the reliability and quality of real-time video streaming by implementing a retransmission scheme that integrates the real-time streaming protocol (RTSP) and the software-defined network capabilities (SDN). Conventional data transmission approaches, like those based on TCP, often suffer from high latency and diminished reliability when managing multiple retransmission requests. To address these issues, we implemented the proposed framework in the SDN switches, including a retransmission mechanism that incorporates a buffering agent to mitigate packet loss. Moreover, by utilizing SDN controllers to create a reliable UDP scheme for efficient data transmission, the framework strengthens both practicality and reliability. The framework’s effectiveness is evaluated using 3 quality assessment metrics, and it demonstrates superior performance with a slight compromise in terms of latency compared to standard RTSP-based streaming. These findings suggest that the proposed solution offers a viable and efficient approach to improve real-time video streaming quality in scenarios where packet loss is prevalent.
{"title":"An SDN-Driven Reliable Transmission Architecture for Enhancing Real-Time Video Streaming Quality","authors":"Ming-Hung Wang, Ting-Shen Hsieh, Yu-Yao Tseng, Po-Wen Chi","doi":"10.1109/mmul.2023.3326835","DOIUrl":"https://doi.org/10.1109/mmul.2023.3326835","url":null,"abstract":"This paper introduces a novel framework designed to enhance the reliability and quality of real-time video streaming by implementing a retransmission scheme that integrates the real-time streaming protocol (RTSP) and the software-defined network capabilities (SDN). Conventional data transmission approaches, like those based on TCP, often suffer from high latency and diminished reliability when managing multiple retransmission requests. To address these issues, we implemented the proposed framework in the SDN switches, including a retransmission mechanism that incorporates a buffering agent to mitigate packet loss. Moreover, by utilizing SDN controllers to create a reliable UDP scheme for efficient data transmission, the framework strengthens both practicality and reliability. The framework’s effectiveness is evaluated using 3 quality assessment metrics, and it demonstrates superior performance with a slight compromise in terms of latency compared to standard RTSP-based streaming. These findings suggest that the proposed solution offers a viable and efficient approach to improve real-time video streaming quality in scenarios where packet loss is prevalent.","PeriodicalId":13240,"journal":{"name":"IEEE MultiMedia","volume":"162 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135158273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The significance of low-quality data in unlabeled medical images is always underestimated. We believe that these underestimated data contain valuable information that remains largely unexplored. We present a novel uncertainty-guided different levels of pseudo-labels (UDLP) framework to explore the underestimated data in medical images. The framework consists of a student-teacher model that uses uncertainty to classify the pseudo-labels predicted by the teacher model into three levels: high confidence, low confidence and unreliability. The student model learns directly from high-confidence pseudo-labels. By using the confident learning method in low-confidence pseudo-labels, the teacher model corrects the noisy labels in low-confidence voxels to provide positive feature information for the student model. We design a method for removing unreliable pseudo-labels, to further enhance model’s generalizability. The proposed framework UDLP is evaluated on two datasets and demonstrates superior performance compared to other state-of-the-art methods.
{"title":"Uncertainty-guided different levels of pseudo-labels for semi-supervised medical image segmentation","authors":"Hengfan Li, Xinwei Hong, Guohua Huang, Xuanbo Xu, Qingfeng Xia","doi":"10.1109/mmul.2023.3329006","DOIUrl":"https://doi.org/10.1109/mmul.2023.3329006","url":null,"abstract":"The significance of low-quality data in unlabeled medical images is always underestimated. We believe that these underestimated data contain valuable information that remains largely unexplored. We present a novel uncertainty-guided different levels of pseudo-labels (UDLP) framework to explore the underestimated data in medical images. The framework consists of a student-teacher model that uses uncertainty to classify the pseudo-labels predicted by the teacher model into three levels: high confidence, low confidence and unreliability. The student model learns directly from high-confidence pseudo-labels. By using the confident learning method in low-confidence pseudo-labels, the teacher model corrects the noisy labels in low-confidence voxels to provide positive feature information for the student model. We design a method for removing unreliable pseudo-labels, to further enhance model’s generalizability. The proposed framework UDLP is evaluated on two datasets and demonstrates superior performance compared to other state-of-the-art methods.","PeriodicalId":13240,"journal":{"name":"IEEE MultiMedia","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134891009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.1109/MMUL.2023.3243209
Fanjie Li, Xiao Hu
Despite the advances in context-aware background music (BM) recommendation, automated BM selection for studying-related contexts is still challenging in that the BM has to not only increase users’ activation and task engagement but also avoid distraction. This study investigated how characteristics of BM linked to users’ perceptions on task engagement and distraction. In a one-week naturalistic user experiment, 30 participants performed their everyday learning-related tasks with music selected by a BM player. We captured participants’ learning contexts and perceptions via pop-up surveys and extracted fine-grained acoustic features for each song in their music listening history via audio processing techniques. Our findings support the power of music in fostering positive studying experience (e.g., perceived engagement) and reveal how several BM characteristics may link to perceived engagement in certain (but not all) conditions. Findings are discussed in relation to theoretical BM studies and implications for generating personalized and context-sensitive BM selections in music-enhanced learning environments.
{"title":"Background Music for Studying: A Naturalistic Experiment on Music Characteristics and User Perception","authors":"Fanjie Li, Xiao Hu","doi":"10.1109/MMUL.2023.3243209","DOIUrl":"https://doi.org/10.1109/MMUL.2023.3243209","url":null,"abstract":"Despite the advances in context-aware background music (BM) recommendation, automated BM selection for studying-related contexts is still challenging in that the BM has to not only increase users’ activation and task engagement but also avoid distraction. This study investigated how characteristics of BM linked to users’ perceptions on task engagement and distraction. In a one-week naturalistic user experiment, 30 participants performed their everyday learning-related tasks with music selected by a BM player. We captured participants’ learning contexts and perceptions via pop-up surveys and extracted fine-grained acoustic features for each song in their music listening history via audio processing techniques. Our findings support the power of music in fostering positive studying experience (e.g., perceived engagement) and reveal how several BM characteristics may link to perceived engagement in certain (but not all) conditions. Findings are discussed in relation to theoretical BM studies and implications for generating personalized and context-sensitive BM selections in music-enhanced learning environments.","PeriodicalId":13240,"journal":{"name":"IEEE MultiMedia","volume":"30 1","pages":"62-72"},"PeriodicalIF":3.2,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41368964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.1109/MMUL.2022.3191680
Yuqing Ding, Z. Wu, Liyang Xie
Video-on-Demand (VoD) streaming services on the hybrid P2P-CDN architecture nicely balance the high reliability contributed by the CDN, and the great scalability provided by P2P. However, the unmanageable and trustless feature of the P2P network can cause content piracy and security threats to the copyright holders and users. To date, there has not been an adequate scheme based on P2P-CDN providing VoD streaming services in the literature that resolves the content protection and secure delivery while keeping up the efficiency of P2P streaming performance. In this work, a manageable and secure VoD streaming delivery scheme is proposed for P2P-CDN, which marries the requisite requirements with the blockchain and zero-knowledge. The experimental results show that our proposed scheme offers a superior VoD streaming service both on the performance metrics and security compared with the most widely used and mature system for P2P-CDN nowadays, even under a large-scale P2P network.
{"title":"Enabling Manageable and Secure Hybrid P2P-CDN Video-on-Demand Streaming Services Through Coordinating Blockchain and Zero Knowledge","authors":"Yuqing Ding, Z. Wu, Liyang Xie","doi":"10.1109/MMUL.2022.3191680","DOIUrl":"https://doi.org/10.1109/MMUL.2022.3191680","url":null,"abstract":"Video-on-Demand (VoD) streaming services on the hybrid P2P-CDN architecture nicely balance the high reliability contributed by the CDN, and the great scalability provided by P2P. However, the unmanageable and trustless feature of the P2P network can cause content piracy and security threats to the copyright holders and users. To date, there has not been an adequate scheme based on P2P-CDN providing VoD streaming services in the literature that resolves the content protection and secure delivery while keeping up the efficiency of P2P streaming performance. In this work, a manageable and secure VoD streaming delivery scheme is proposed for P2P-CDN, which marries the requisite requirements with the blockchain and zero-knowledge. The experimental results show that our proposed scheme offers a superior VoD streaming service both on the performance metrics and security compared with the most widely used and mature system for P2P-CDN nowadays, even under a large-scale P2P network.","PeriodicalId":13240,"journal":{"name":"IEEE MultiMedia","volume":"30 1","pages":"36-51"},"PeriodicalIF":3.2,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42026429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.1109/MMUL.2022.3208923
Muhammad Awais Hussain, Chun-Lin Lee, T. Tsai
This article proposes an efficient audio incremental learning method to reduce the computational complexity and catastrophic forgetting during the incremental addition of the audio data in deep neural networks. The computational complexity is reduced by performing training of only fully connected layers and catastrophic forgetting is reduced by sharing the knowledge from the old learned classes without using previously learned data. Our method has been evaluated extensively on UrbanSound8K, ESC-10, and TUT datasets where the state-of-the-art accuracies have been achieved. Moreover, our method has been evaluated on Nvidia 1080-ti GPU, Nvidia TX-2, and Nvidia Xavier development boards to demonstrate the training time and energy consumption savings as compared to the recent state-of-the-art methods.
{"title":"An Efficient Incremental Learning Algorithm for Sound Classification","authors":"Muhammad Awais Hussain, Chun-Lin Lee, T. Tsai","doi":"10.1109/MMUL.2022.3208923","DOIUrl":"https://doi.org/10.1109/MMUL.2022.3208923","url":null,"abstract":"This article proposes an efficient audio incremental learning method to reduce the computational complexity and catastrophic forgetting during the incremental addition of the audio data in deep neural networks. The computational complexity is reduced by performing training of only fully connected layers and catastrophic forgetting is reduced by sharing the knowledge from the old learned classes without using previously learned data. Our method has been evaluated extensively on UrbanSound8K, ESC-10, and TUT datasets where the state-of-the-art accuracies have been achieved. Moreover, our method has been evaluated on Nvidia 1080-ti GPU, Nvidia TX-2, and Nvidia Xavier development boards to demonstrate the training time and energy consumption savings as compared to the recent state-of-the-art methods.","PeriodicalId":13240,"journal":{"name":"IEEE MultiMedia","volume":"30 1","pages":"84-90"},"PeriodicalIF":3.2,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45958965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：