Multimedia Communication

Paper accepted: LiDeR: Lightweight Dense Residual Network for Video Super-Resolution on Mobile Devices

IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP 2022)

June 26-29, 2022 | Nafplio, Greece

Conference Website

[Video]

Ekrem Çetinkaya (Christian Doppler Laboratory ATHENA, Alpen-Adria-Universität Klagenfurt), Minh Nguyen (Christian Doppler Laboratory ATHENA, Alpen-Adria-Universität Klagenfurt), and Christian Timmerer (Christian Doppler LaboratoryATHENA, Alpen-Adria-Universität Klagenfurt)

 

Abstract: Video is now an essential part of the Internet. The increasing popularity of video streaming on mobile devices and the improvement in mobile displays brought together challenges to meet user expectations. Advancements in deep neural networks have seen successful applications on several computer vision tasks such as super-resolution (SR). Although DNN-based SR methods significantly improve over traditional methods, their computational complexity makes them challenging to apply on devices with limited power, such as smartphones. However, with the improvement in mobile hardware, especially GPUs, it is now possible to use DNN based solutions, though existing DNN based SR solutions are still too complex. This paper proposes LiDeR, a lightweight video SR network specifically tailored toward mobile devices. Experimental results show that LiDeR can achieve competitive SR performance with state-of-the-art networks while improving the execution speed significantly, i.e., 267 % for X4 upscaling and 353 % for X2 upscaling compared to ESPCN.

Keywords: Super-resolution, Mobile machine learning, Video super-resolution.

 

Paper accepted: Detection and Localization of Video Transcoding From AVC to HEVC Based on Deep Representations of Decoded Frames and PU Maps

Detection and Localization of Video Transcoding From AVC to HEVC Based on Deep Representations of Decoded Frames and PU Maps

IEEE Transactions on Multimedia

Haichao Yao (Beijing Jiaotong University), Rongrong Ni (Beijing Jiaotong University), Hadi Amirpour (Alpen-Adria-Universität Klagenfurt), Christian Timmerer (Alpen-Adria-Universität Klagenfurt)Yao Zhao (Beijing Jiaotong University).

Hadi
,

Hadi Amirpour to give a talk at Fraunhofer FOKUS MWS

Video Encoding Optimizations for Live Video Streaming

FOKUS Media Web Symposium

20th – 24th June 2022 | Berlin, Germany

 

Abstract: Live video streaming is expected to become mainstream in the fifth-generation (5G) mobile networks. Optimizing video encoding for live video streaming is challenging due to the latency introduced by any optimization method. In this talk, we introduce low-latency video optimization methods that are utilized to improve the quality of video encodings by predicting optimized encoding parameters.

Hadi Amirpour is a postdoc research fellow at ATHENA  directed by Prof. Christian Timmerer. He received his B.Sc. degrees in Electrical and Biomedical Engineering, and he pursued his M.Sc. in Electrical Engineering. He got his Ph.D. in computer science from the University of Klagenfurt in 2022. He was appointed co-chair of Task Force 7 (TF7) Immersive Media Experience (IMEx) at the 15th Qualinet meeting. He was involved in the project EmergIMG, a Portuguese consortium on emerging imaging technologies, funded by the Portuguese funding agency and H2020. Currently, he is working on the ATHENA project in cooperation with its industry partner Bitmovin. His research interests are image processing and compression, video processing and compression, quality of experience, emerging 3D imaging technology, and medical image analysis.

Hadi
,

IEEE Transactions on Multimedia: Detection and Localization of Video Transcoding From AVC to HEVC Based on Deep Representations of Decoded Frames and PU Maps

Authors: Haichao Yao (Beijing Jiaotong University), Rongrong Ni (Beijing Jiaotong University), Hadi Amirpour (Alpen-Adria-Universität Klagenfurt), Christian Timmerer (Alpen-Adria-Universität Klagenfurt)Yao Zhao (Beijing Jiaotong University).

ATHENA at ACM MMSys Conference 2022

The 13th ACM Multimedia Systems Conference MMSys’22

14th – 17th June 2022 | Athlone, Ireland.

Conference Website

The ACM Multimedia Systems Conference (MMSys) provides a forum for researchers to present and share their latest research findings in multimedia systems. While research about specific aspects of multimedia systems is regularly published in the various proceedings and transactions of the networking, operating systems, real-time systems, databases, mobile computing, distributed systems, computer vision, and middleware communities, MMSys aims to cut across these domains in the context of multimedia data types.

This year, MMSys hosted around 150 on-site participants from academia and industry. Five ATHENA members travelled to Athlone, Ireland, to present four papers by Reza Farahani, Babak Taraghi, and Vignesh V Menon in two tracks, i.e., Open Dataset & Software Track and Demo & Industry Track.

Moreover, two presentations in Mentoring & Postdoc Networking event by ATHENA postdocs:

  • Hadi Amirpour,  “Video Encoding Optimization for Live Video Streaming” (pdf)
  • Farzad Tashtarian, “QoE Optimization in Live Streaming” (pdf)

 

ACSD’22: The Power in Your Pocket: Boosting Video Quality with Super-Resolution on Mobile Devices

We presented the poster “The Power in Your Pocket: Boosting Video Quality with Super-Resolution on Mobile Devices” at the Austrian Computer Science Day 2022 conference. The poster summarizes research about improving the visual quality of video streaming on mobile devices by utilizing deep neural network-based enhancement techniques.

Here is the list of papers that we cover in the poster:

  1. Super-resolution Based Bitrate Adaptation for HTTP Adaptive Streaming for Mobile Devices

  2. MoViDNN: A Mobile Platform for Evaluating Video Quality Enhancement with Deep Neural Networks

, , ,

ITEC @ LNDF was a big success

This years´s “Lange Nacht der Forschung” took place on May 20, 2022. The LNDF is Austria´s most significant national research event to present the accomplishments to the broad public. ITEC was represented by three stations and involved in the station of Computer Games and Engineering, and it was a fantastic experience for everyone! We tried to make our research easily understandable for everyone.

 

,

Paper Accepted: Efficient Transparent Access to 5G Edge Services

1st International Workshop on Edge Network Softwarization (ENS 2022) co-located with IEEE International Conference on Network Softwarization (NetSoft 2022)  Milan, Italy

Authors: Josef Hammer and Hermann Hellwagner, Alpen-Adria-Universität Klagenfurt

Abstract: Multi-access Edge Computing (MEC) is a central piece of 5G telecommunication systems and is essential to satisfy the challenging low-latency demands of future applications. MEC provides a cloud computing platform at the edge of the radio access network that developers can utilize for their applications. In [1] we argued that edge computing should be transparent to clients and introduced a solution to that end. This paper presents how to efficiently implement such a transparent approach, leveraging Software-Defined Networking. For high performance and scalability, our architecture focuses on three aspects: (i) a modular architecture that can easily be distributed onto multiple switches/controllers, (ii) multiple filter stages to avoid screening traffic not intended for the edge, and (iii) several strategies to keep the number of flows low to make the best use of the precious flow table memory in hardware switches. A performance evaluation is shown, with results from a real edge/fog testbed.

Keywords: 5G, Multi-Access Edge Computing, MEC, Patricia Trie, SDN, Software-Defined Networking

Hadi
,

Paper accepted: Video Complexity Dataset at the 13th ACM Multimedia Systems Conference (ODS) track

Title: Video Complexity Dataset (VCD)

The 13th ACM Multimedia Systems Conference (ACM MMSys 2022) Open Dataset and Software (ODS) track

June 14–17, 2022 |  Athlone, Ireland

Authors: Hadi Amirpour (Alpen-Adria-Universität Klagenfurt), Vignesh V Menon (Alpen-Adria-Universität Klagenfurt), Samira Afzal (Alpen-Adria-Universität Klagenfurt), Mohammad Ghanbari (School of Computer Science and Electronic Engineering, University of Essex, Colchester, UK), and Christian Timmerer (Alpen-Adria-Universität Klagenfurt).

Abstract: This paper provides an overview of the open Video Complexity Dataset (VCD) which comprises 500 Ultra High Definition (UHD) resolution test video sequences. These sequences are provided at 24 frames per second (fps) and stored online in losslessly encoded 8-bit 4:2:0 format. In this paper, all sequences are characterized by spatial and temporal complexities, rate-distortion complexity, and encoding complexity with the x264 AVC/H.264 and x265 HEVC/H.265 video encoders. The dataset is tailor-made for cutting-edge multimedia applications such as video streaming, two-pass encoding, per-title encoding, scene-cut detection, etc. Evaluations show that the dataset includes diversity in video complexities. Hence, using this dataset is recommended for training and testing video coding applications. All data have been made publicly available as part of the dataset, which can be used for various applications.
The details of VCD can be accessed online at https://vcd.itec.aau.at.

Farzad Tashtarian to give a short talk at CHIST-ERA conference

Optimizing QoE in Live Streaming over Wireless Networks using Machine Learning Techniques

May 25, 2022, Edinburgh, UK

Empowered by today’s rich tools for media generation and collaborative production and the convenient wireless access (e.g., WiFi and cellular networks) to the Internet, crowdsourced live streaming over wireless networks have become very popular. However, crowdsourced wireless live streaming presents unique video delivery challenges that make a difficult tradeoff among three core factors: bandwidth, computation/storage, and latency. However, [read more]