Article
Computer Science, Information Systems
Prateek Agrawal, Anatoliy Zabrovskiy, Adithyan Ilangovan, Christian Timmerer, Radu Prodan
Summary: This paper proposes a new method for fast video transcoding time prediction and scheduling, which consists of three phases to predict and schedule the transcoding time of x264 encoded videos. Experimental results show that the predictive model reduces transcoding errors and time, demonstrating the effectiveness of the method.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Shin-Hung Chang, Min-Lun Tsai, Meng-Huang Lee, Jan-Ming Ho
Summary: Different resolutions can impact users' quality of experience (QoE) for different video scenes. High-resolution segments are more suitable for fast motion scenes, while low-resolution segments perform better in slow motion scenes. Optimizing the arrangement of segments based on resolution may maximize users' viewing satisfaction.
INTERNATIONAL JOURNAL OF INTERACTIVE MULTIMEDIA AND ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Information Systems
Yuanxing Zhang, Yushuo Guan, Kaigui Bian, Yunxin Liu, Hu Tuo, Lingyang Song, Xiaoming Li
Summary: This article introduces a 360-degree video streaming system named EPASS360, which utilizes ensemble prediction and allocation methods to deliver a high Quality of Experience (QoE) for 360-degree videos. By leveraging ensemble learning and QoE-aware optimization, high prediction accuracy and efficient resource allocation are achieved.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2021)
Article
Computer Science, Information Systems
Jiawei Huang, Qichen Su, Weihe Li, Zhuoran Liu, Tao Zhang, Sen Liu, Ping Zhong, Wanchun Jiang, Jianxin Wang
Summary: The article proposes a client-side building block named OCRM to help ABR algorithms improve user viewing experience and network utilization by opportunistically transmitting high-quality chunks to the client, resulting in up to 35% improvement in user experience.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2022)
Article
Automation & Control Systems
Jingzheng Tu, Cailian Chen, Ziwen Yang, Mingyan Li, Qimin Xu, Xinping Guan
Summary: 360 degrees video is attractive for industrial surveillance in smart factories due to its immersive experience. However, transmitting this video requires a large bandwidth due to its high-resolution and panoramic view. This article proposes a perception-sensitivity-based tiled video streaming method called PSTile for industrial surveillance. It optimizes surveillance accuracy, end-to-end latency, and quality-of-experience under accuracy, latency, and bandwidth constraints. Simulations show that PSTile achieves lower latency and higher video bitrate compared to other methods.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Adam Polakovic, Gregor Rozinaj, Gabriel-Miro Muntean
Summary: This paper presents a novel algorithm for omnidirectional video delivery, utilizing spatial tiling and multiple tiling schemes to achieve bandwidth savings and adaptation latency reduction. The proposed algorithm reduces network bandwidth requirements to about 30% of the original value with a low processing latency of 70.87 ms.
IEEE TRANSACTIONS ON BROADCASTING
(2022)
Article
Computer Science, Interdisciplinary Applications
Jelena Vlaovic, Snjezana Rimac-Drlje, Drago Zagar, Luka Filipovic
Summary: The need for standardization in video streaming technologies led to the development of MPEG DASH, ensuring smooth playback for end-users. While the client side adaptation logic has been extensively researched, the server side remains less explored. This article proposes a methodology for optimal spatial resolution selection in MPEG DASH, improving the segmentation process for better video quality.
JOURNAL OF INDUSTRIAL INFORMATION INTEGRATION
(2021)
Review
Computer Science, Information Systems
Federico Chiariotti
Summary: The commercialization of Virtual Reality (VR) headsets has generated intense interest in immersive and 360-degree video streaming in industry and research communities. Specific challenges such as omnidirectional video coding, Quality of Experience (QoE), saliency measurement, and adaptive streaming have been key focuses in the latest literature on this topic.
COMPUTER COMMUNICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Roberto Viola, Angel Martin, Javier Morgade, Stefano Masneri, Mikel Zorrilla, Pablo Angueira, Jon Montalban
Summary: Future telecommunication networks are expected to outperform current networks in terms of key performance indicators due to increasing consumption of video streams and demand for higher quality content. Content delivery networks (CDNs) are used to enhance media availability and delivery performance across the Internet, but extreme concurrency dynamics can impact CDN capacity and performance. Therefore, network accelerators are needed to enforce CDN resilience and efficient utilization, as well as to achieve reliable and cost-effective content delivery through predictive CDN adaptability and business constraints.
IEEE TRANSACTIONS ON BROADCASTING
(2021)
Article
Computer Science, Software Engineering
Zhenxiao Luo, Baili Chai, Zelong Wang, Miao Hu, Di Wu
Summary: This paper presents a practical neural- enhanced 360-degree video streaming framework called Masked360, which can significantly reduce bandwidth consumption and achieve robustness against packet loss. By transmitting masked low-resolution versions of video frames, the server can reduce bandwidth significantly, and the client can reconstruct the original frames for playback. The paper also proposes optimization techniques to further improve video streaming quality.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2023)
Article
Computer Science, Software Engineering
Zhenxiao Luo, Baili Chai, Zelong Wang, Miao Hu, Di Wu
Summary: In this paper, a practical neural-enhanced 360-degree video streaming framework called Masked360 is proposed to reduce bandwidth consumption and achieve robustness against packet loss. Masked360 achieves bandwidth reduction by transmitting masked low-resolution video frames and employs optimization techniques to improve video quality. Experimental results show that Masked360 can achieve 4K video streaming with bandwidth as low as 2.4 Mbps and significantly improve video quality compared to other baselines in terms of PSNR and SSIM.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2023)
Article
Computer Science, Information Systems
Weihe Li, Jiawei Huang, Shiqi Wang, Chuliang Wu, Sen Liu, Jianxin Wang
Summary: Video traffic has been growing exponentially due to the increasing popularity of mobile devices and network improvements. Most commercial players use adaptive bitrate algorithms to choose bitrates based on network capacity and buffer occupancy. However, current algorithms prioritize average bitrate over perceptual quality, resulting in a degraded Quality of Experience (QoE). To tackle this issue, we propose DAVS (Dynamic-chunk quality Aware Video Streaming), an adaptive bitrate algorithm that employs apprenticeship learning to select higher quality for dynamic chunks without sacrificing static chunk quality excessively. Additionally, DAVS takes into account user viewing preferences to adapt to QoE diversity. Experimental results demonstrate that DAVS improves the quality of dynamic chunks and significantly enhances QoE compared to other representative algorithms.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Information Systems
Yili Jin, Junhua Liu, Fangxin Wang, Shuguang Cui
Summary: 360 degrees panoramic videos have been booming due to the desire for immersive and interactive experiences, but they pose challenges such as uncertain user Field of View, sensitive delay tolerance, and high bandwidth requirement. This article proposes Ebublio, an intelligent edge caching framework, to address these challenges and optimize user Quality of Experience and system cost.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Ryuta Sakamoto, Takahiro Shobudani, Ryosuke Hotchi, Ryogo Kubo
Summary: This paper proposes a bitrate selection method in adaptive video streaming for MPEG-DASH to improve QoE by minimizing bitrate fluctuation. The method maintains playback buffer level, avoids high-frequency video bitrate switching, and enhances user experience quality.
IEICE TRANSACTIONS ON COMMUNICATIONS
(2021)
Review
Chemistry, Multidisciplinary
En Sing Wong, Nur Haliza Abdul Wahab, Faisal Saeed, Nouf Alharbi
Summary: In recent years, the use of 360-degree videos has become increasingly prevalent in various sectors, driving the development of a highly immersive, smooth virtual reality environment. To address the challenges faced in real-time streaming of 360-degree videos, various streaming methods and network optimization strategies have been discussed to enhance the Quality of Experience (QoE) and Quality of Service (QoS) of VR services.
APPLIED SCIENCES-BASEL
(2022)
Article
Multidisciplinary Sciences
Yupei Chen, Zhibo Yang, Seoyoung Ahn, Dimitris Samaras, Minh Hoai, Gregory Zelinsky
Summary: The study introduces a new dataset of goal-directed search eye movements called COCO-Search18, providing laboratory-quality data for training deep network models. Different machine learning methods were used to benchmark the dataset, resulting in new state-of-the-art models for predicting goal-directed search fixations.
SCIENTIFIC REPORTS
(2021)
Review
Biochemical Research Methods
Jianyuan Deng, Zhibo Yang, Iwao Ojima, Dimitris Samaras, Fusheng Wang
Summary: Artificial intelligence (AI) has played a crucial role in drug discovery over the past decade, with applications ranging from virtual screening to drug design. This survey provides a comprehensive overview of AI in drug discovery, covering tasks, data resources, model architectures, and learning paradigms.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Computer Science, Hardware & Architecture
Arani Bhattacharya, Caitao Zhan, Abhishek Maji, Himanshu Gupta, Samir R. Das, Petar M. Djuric
Summary: The paper addresses the issue of localizing unauthorized transmitters using a distributed set of sensors and develops greedy approximation algorithms to maximize localization accuracy. By reducing time complexity, the techniques demonstrate significant performance improvements across various simulation platforms.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2022)
Proceedings Paper
Computer Science, Theory & Methods
Yupei Chen, Zhibo Yang, Souradeep Chakraborty, Sounak Mondal, Seoyoung Ahn, Dimitris Samaras, Minh Hoai, Gregory Zelinsky
Summary: This study rigorously evaluates target-absent search behavior and finds that there is a weak target guidance signal in such searches compared to target-present searches. Additionally, the study explores stopping criteria in target-absent searches and proposes a model that combines target detection representation, fixation history, and subject ID to better predict when a person stops paying attention during such searches.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhibo Yang, Muhammet Bastan, Xinliang Zhu, Doug Gray, Dimitris Samaras
Summary: Proxy-based metric learning losses, by imposing hierarchical structure on the proxies, are able to capture both class-discriminative features and class-shared characteristics, thereby improving the performance of image retrieval, especially on large datasets with strong hierarchical structure.
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022)
(2022)
Proceedings Paper
Computer Science, Information Systems
Roberto Calvo-Palomino, Arani Bhattacharya, Gerome Bovet, Domenico Giustiniano
2020 21ST IEEE INTERNATIONAL SYMPOSIUM ON A WORLD OF WIRELESS, MOBILE AND MULTIMEDIA NETWORKS (IEEE WOWMOM 2020)
(2020)
Proceedings Paper
Computer Science, Information Systems
Vasudevan Nagendra, Arani Bhattacharya, Vinod Yegneswaran, Amir Rahmati, Samir Das
WEB CONFERENCE 2020: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2020)
(2020)
Proceedings Paper
Computer Science, Hardware & Architecture
Mallesham Dasari, Arani Bhattacharya, Santiago Vargas, Pranjal Sahu, Aruna Balasubramanian, Samir R. Das
IEEE INFOCOM 2020 - IEEE CONFERENCE ON COMPUTER COMMUNICATIONS
(2020)
Proceedings Paper
Computer Science, Hardware & Architecture
Arani Bhattacharya, Caitao Zhan, Himanshu Gupta, Samir R. Das, Petar M. Djuric
IEEE INFOCOM 2020 - IEEE CONFERENCE ON COMPUTER COMMUNICATIONS
(2020)
Proceedings Paper
Computer Science, Information Systems
Caitao Zhan, Himanshu Gupta, Arani Bhattacharya, Mohammad Ghaderibaneh
2020 19TH ACM/IEEE INTERNATIONAL CONFERENCE ON INFORMATION PROCESSING IN SENSOR NETWORKS (IPSN 2020)
(2020)
Article
Telecommunications
Arani Bhattacharya, Ayon Chakraborty, Samir R. Das, Himanshu Gupta, Petar M. Djuric
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING
(2020)