4,480 Hits in 10.7 sec

A Deep Graph Reinforcement Learning Model for Improving User Experience in Live Video Streaming [article]

Stefanos Antaris, Dimitrios Rafailidis, Sarunas Girdzijauskas
2021 arXiv   pre-print
In this paper we present a deep graph reinforcement learning model to predict and improve the user experience during a live video streaming event, orchestrated by an agent/tracker.  ...  In addition, provided that past events have various user experience characteristics we follow a gradient boosting strategy to compute a global model that learns from different events.  ...  CONCLUSIONS In this paper, we presented a deep graph reinforcement learning model for improving the experience of each viewer when attending enterprise live video streaming events.  ... 
arXiv:2107.13619v1 fatcat:iyi2fylrwfgcnb3ton3r7kskbe

Multimedia Edge Computing [article]

Zhi Wang, Wenwu Zhu, Lifeng Sun, Han Hu, Ge Ma, Ming Ma, Haitian Pang, Jiahui Ye, Hongshan Li
2021 arXiv   pre-print
to optimize the quality of experience for multimedia services at the last mile proactively.  ...  to performing distributed machine learning over such data using the joint edge and cloud infrastructure and using evolutional strategies like reinforcement learning and online learning at edge devices  ...  For example, the trending live streaming has been optimized to utilize edge devices as the initial streaming relays, so as to improve the broadcaster's upload quality, which in turn improves the overall  ... 
arXiv:2105.02409v1 fatcat:26eyjzgg2na2lep2crb4cfhs7m

Meta-Reinforcement Learning via Buffering Graph Signatures for Live Video Streaming Events [article]

Stefanos Antaris, Dimitrios Rafailidis, Sarunas Girdzijauskas
2021 arXiv   pre-print
In this study, we present a meta-learning model to adapt the predictions of the network's capacity between viewers who participate in a live video streaming event.  ...  We evaluate the proposed model on the link weight prediction task on three real-world datasets of live video streaming events.  ...  Recently, GELS employed gradient boosting to extract information from past streaming events for improving user experience [10] .  ... 
arXiv:2111.09412v1 fatcat:3mml2xxlrrconkowa4kkvncoee

A Review of Predictive Quality of Experience Management in Video Streaming Services

Maria Torres Vega, Cristian Perra, Filip De Turck, Antonio Liotta
2018 IEEE transactions on broadcasting  
Satisfying the requirements of devices and users of online video streaming services is a challenging task.  ...  Herein, we review the most significant 'predictive' QoE management methods for video streaming services, showing how different machine learning approaches may be used to perform proactive control.  ...  Online and Reinforcement Learning: Q-Learning, SARSA, Markov,… Deep Reinforcement Learning: Artificial Neural Networks + Reinforcement, … Yes No Improve modelling inputs Feedback to improve  ... 
doi:10.1109/tbc.2018.2822869 fatcat:tcdvi4ngbzcw5di5xre5escmiq

Optimal Skipping Rates: Training Agents with Fine-Grained Control Using Deep Reinforcement Learning

Adil Khan, Jiang Feng, Shaohui Liu, Muhammad Zubair Asghar
2019 Journal of Robotics  
Similarly, ViZDoom is a game artificial intelligence research platform based on Doom used for visual deep reinforcement learning in 3D game environments such as first-person shooters (FPS).  ...  In this paper, how the frame skipping rate influences the agent's learning and final performance is proposed, particularly using deep Q-learning, experience replay memory, and the ViZDoom Game AI research  ...  Deep Q-learning, a method of deep reinforcement learning (see Section 2), is used to learn the policy. In order to experiment, the problem is modeled as a Markov Decision Process (MDP).  ... 
doi:10.1155/2019/2970408 fatcat:u3fouzkq7rdvhkkwc3j67qeusa

Predicting the Session of an P2P IPTV User through Support Vector Regression (SVR)

M. Ali, I. Ullah, W. Noor, A. Sajid, A. Basit, J. Baber
2020 Zenodo  
In this paper, a model based on machine learning is proposed in order to predict the length of a user session on entering the network.  ...  Furthermore, it will also enable service providers to identify stable peers in a live video streaming network.  ...  In order to improve the performance of P2P live video streaming systems, many researchers have modeled different aspects of user behavior.  ... 
doi:10.5281/zenodo.4016218 fatcat:bmqt5rfp6zerhp3s3yyz2bxvxa

Quality Enhanced Multimedia Content Delivery for Mobile Cloud with Deep Reinforcement Learning

Muhammad Saleem, Yasir Saleem, H. M. Shahzad Asif, M. Saleem Mian
2019 Wireless Communications and Mobile Computing  
The multimedia streaming with limited bandwidth and varying network environment for mobile users affects the user quality of experience.  ...  The dynamic adaptive streaming over HTTP is an efficient scheme for bitrate adaptation in which video is segmented and stored in different quality levels.  ...  This results in frequent quality switches and video freezing which can decrease user QoE for video streaming.  ... 
doi:10.1155/2019/5038758 fatcat:ez4aoo66yfcn7nscoptprdxppi

RL-OPRA: Reinforcement Learning for Online and Proactive Resource Allocation of crowdsourced live videos

Emna Baccour, Aiman Erbad, Amr Mohamed, Fatima Haouari, Mohsen Guizani, Mounir Hamdi
2020 Future generations computer systems  
As the optimization is not adequate for online serving, we propose a real-time approach based on Reinforcement Learning (RL), namely RL-OPRA, which adaptively learns to optimize the allocation and serving  ...  To ensure a better Quality of Experience (QoE), higher availability, and lower costs, large live streaming CPs are migrating their services to geo-distributed cloud infrastructure.  ...  Reinforcement learning for online and proactive resource allocation In this section, we formulate the resource allocation of crowdsourcing live videos as a reinforcement learning process.  ... 
doi:10.1016/j.future.2020.06.038 fatcat:ljocsvdztbcudb4czuw2k7cera

Multi-Task Learning for User Engagement and Adoption in Live Video Streaming Events [article]

Stefanos Antaris and Dimitrios Rafailidis and Romina Arriaza
2021 arXiv   pre-print
In this paper we present a multi-task deep reinforcement learning model to select the time of a live video streaming event, aiming to optimize the viewer's engagement and adoption at the same time.  ...  Nowadays, live video streaming events have become a mainstay in viewer's communication in large international enterprises.  ...  To address the shortcomings of state-of-the-art strategies, in this study we propose a Multi-task lEaRning model for user engagement and adoption in Live vIdeo streamiNg events (MERLIN), making the following  ... 
arXiv:2106.10305v1 fatcat:colemm4i7ngxrkljvi32333q5e

Deep Learning for Edge Computing Applications: A State-of-the-art Survey

Fangxin Wang, Miao Zhang, Xiangxiang Wang, Xiaoqiang Ma, Jiangchuan Liu
2020 IEEE Access  
Besides, the recent breakthroughs in deep learning have greatly facilitated the data processing capacity, enabling a thrilling development of novel applications, such as video surveillance and autonomous  ...  In this article, we provide a comprehensive survey of the latest efforts on the deep-learning-enabled edge computing applications and particularly offer insights on how to leverage the deep learning advances  ...  with reduced filter numbers in each layer. 2) ADAPTIVE STREAMING Adaptive video streaming [78] is becoming a critical issue in today's video delivery to provide the best quality of experience (QoE  ... 
doi:10.1109/access.2020.2982411 fatcat:43atfhktujbuxns2bsl2cfpnay

Guest Editorial: Special Section on Data Analytics and Machine Learning for Network and Service Management–Part I

Nur Zincir-Heywood, Giuliano Casale, David Carrera, Lydia Y. Chen, Amogh Dhamdhere, Takeru Inoue, Hanan Lutfiyya, Taghrid Samak
2020 IEEE Transactions on Network and Service Management  
They present a monitoring solution based on a machine learning model that is able to infer Key Video Quality of Experience Indicators such as stalling, initial delay, video resolution, and average video  ...  "Data Fusion Oriented Graph Convolution Network Model for Rumor Detection," Yu et al. [item 15) in the Appendix] present a rumor detection model based on Graph Convolution Networks.  ... 
doi:10.1109/tnsm.2020.3038736 fatcat:fg3hi7r5vjgpxgamnuq3itgbd4

Deep Reinforcement Learning for Query-Conditioned Video Summarization

Yujia Zhang, Michael Kampffmeyer, Xiaoguang Zhao, Min Tan
2019 Applied Sciences  
reinforcement learning approach.  ...  After that, a deep reinforcement learning-based summarization network (SummNet) is developed to provide personalized summaries by integrating relatedness, representativeness and diversity rewards.  ...  On average, it achieves an improvement of 1.15% in terms of F-measure, which demonstrates that our proposed deep reinforcement learning model together with the proposed mapping mechanism facilitates learning  ... 
doi:10.3390/app9040750 fatcat:5nsbvbpxtjgbfejvm2xgjsxgba

Applied Machine Learning for Games: A Graduate School Course [article]

Yilei Zeng, Aayush Shah, Jameson Thai, Michael Zyda
2021 arXiv   pre-print
In this paper, we describe our machine learning course designed for graduate students interested in applying recent advances of deep learning and reinforcement learning towards gaming.  ...  Our students gained hands-on experience in applying state of the art machine learning techniques to solve real-life problems in gaming.  ...  One project applied realistic and personalized head models in a one-shot setting as an overlay to video game characters. They picked Unity3D Mario model for experiment.  ... 
arXiv:2012.01148v2 fatcat:f44ln32jnbfhrearv234ylteru

Table of Contents

2018 2018 IEEE International Symposium on Multimedia (ISM)  
and on-Demand Tiled HEVC 360 VR Video Streaming SC-Conv: Sparse-Complementary Convolution for Efficient Model Utilization on CNNs 97 Chun-Fu (Richard) Chen (IBM T.J.  ...  Sebastian (Quality and Usability Lab, TU Berlin, and German Research Center for Artificial Intelligence (DFKI)) Light-Weight Video Coding Based on Perceptual Video Quality for Live Streaming 139 Yusuke  ... 
doi:10.1109/ism.2018.00004 fatcat:itdeitfrvfcabi3bnp772wfzte

Near Real-Time Detection of Poachers from Drones in AirSim

Elizabeth Bondi, Ashish Kapoor, Debadeepta Dey, James Piavis, Shital Shah, Robert Hannaford, Arvind Iyer, Lucas Joppa, Milind Tambe
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
However, monitoring the live video stream from these conservation UAVs all night is an arduous task.  ...  The promising results from a field test have led to a plan for larger-scale deployment in a national park in southern Africa.  ...  Acknowledgments This was supported by Microsoft AI for Earth, the National Science Foundation (CCF-1522054), and UCAR N00173-16-2-C903, with the primary sponsor being the Naval Research Laboratory (Z17  ... 
doi:10.24963/ijcai.2018/847 dblp:conf/ijcai/BondiKDPSHIJT18 fatcat:icigzvwpvzhy5b2msplfipgvx4
« Previous Showing results 1 — 15 out of 4,480 results