Organizing Co-chairs
  • Giuseppe Valenzise, CNRS, France
  • Michel Kieffer, Université ParisSaclay, France
  • Shuai Wan, Nortwestern Polytechnical University, China
  • Zhan Ma, Nanjing Univesity, China
  • Deniz Gunduz, Imperial College London, UK
  • Stéphane Coulombe, ETS Montreal, Canada
Technical Program Commitee
  • Fernando Pereira, Instituto Superior Técnico, Portugal
  • Wei Cai, The Chinese University of Hong Kong, Shenzhen, China
  • Weiyao Lin, Shanghai Jiao Tong University, China
  • Christian Timmerer, University of Klagenfurt and Bitmovin, Austria
  • Ali C. Begen, Ozyegin University and Networked Media, Turkey
  • Marco Cagnazzo, University of Padova, Italy
  • Lu Zhang, INSA Rennes, France
  • François-Xavier Coudoux, UPHF, France
  • Frédéric Dufaux, CNRS, France
  • Gil Zussman, Columbia University, US
  • Jiaying Liu, Peking University, China
  • Lukas Krasula, Netflix, US
  • Jing Li, Alibaba, China
  • Hadi Amirpour, University of Klagenfurt, Austria
  • Balu Adsumilli, Google, US
  • Anthony Trioux, Xidian University, China
  • Hui Yuan, Shandong University, China
  • Nikolaos Thomos, University of Essex, UK
  • Abdelhak Bentaleb, Concordia University, Canada
  • Cheng-Hsin Hsu, National Tsing Hua University, Taiwan
  • Fan Li, Xi'an Jiaotong University, China
  • Wei Zhang, Xidian Univeristy, China

The development of applications such as teleoperation of unmanned vehicles or robots, augmented reality, telemedicine, gaming, autonomous driving, and many others, demands nearly instantaneous delivery of multimedia contents. In these scenarios, the overall delay from the source to user or algorithm and the robustness to variations of content and channel characteristics play a pivotal role in shaping the overall system performance and users’ quality of experience. Over the past few decades, substantial efforts have been dedicated to optimizing various sources of delay in multimedia transmission, including ultra-reliable low-latency communication provided by 5G, multimedia compression and adaptive streaming techniques, new control schemes and artificial intelligence tools to predict and manage network, etc. Nevertheless, many challenges remain to achieve effective ultra-low latency (10-50 ms) and robust multimedia delivery, such as dealing with rapidly fluctuating channel and network conditions, mitigating packet loss, employing generative AI tools to reduce the amount of transmitted data, and develop more sophisticated quality of experience models aimed at increasing the efficiency of media delivery.

This ICME workshop on Ultra Low-Latency and Robust Multimedia Delivery intends to gather researchers with diverse and interdisciplinary backgrounds to cover a variety of aspects related to multimedia content delivery, including multimedia compression, network modeling and control, error correction, and multimedia quality assessment, with the goal to develop ultra low-latency and robust media delivery systems and technologies.

Date of the workshop:

19 July 2024, 1 PM - 5 PM, EDT

List of accepted papers:
  • Rate Control Optimizing Model for Constraining Over-Saturated Live Streaming Quality
    Huiwen Ren, Zhao Wang, Siwei Ma (Peking University); Jiexi Wang, Yuwen He, Li Zhang (Bytedance Inc.); Wen Gao (Peking University, China)
  • An End-to-End Channel-Adaptive Feature Compression Approach in Device-Edge Co-Inference Systems
    Yuan Ouyang, Ping Wang, Lijun He, Fan Li (Xi'an Jiaotong University, China)
  • Optimizing An Open VVC Encoder For Low Delay Remote Desktop Applications
    Anastasia Henkel, Jens Brandenburg, Detlev Marpe (Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, Germany); Benjamin Bross, Adam Wieckowski (HHI); Andoni Morales, Sergio Sanchez (Fluendo)
  • Lightweight Texture-Guided Fast Partition Method for Luma and Chroma Intra Coding in VVC
    Zhikai Liu, Zhidao Zhou, Fan Liang, Wei Sun (Sun Yat-sen University, China)
  • Adaptive Bitrate Control with Frame Extrapolation for Ultra Low Latency Video Transmission
    Hind Kanj, François-Xavier COUDOUX, Patrick CORLAY (UMR 8520 - IEMN, DOAE, Univ. Polytechnique Hauts-de-France, CNRS, Univ. Lille, YNCREA, Centrale Lille, France); Michel KIEFFER (Université Paris-Saclay); Marco Cagnazzo (LTCI, Télécom ParisTech, Institut Polytechnique de Paris, France)
Invited talk (Ali Begen):

The Age of TCP is Over, The Time of MOQ has Come


OTT live sports has led sports broadcasting to a new level. Yet, there are still some challenges. For example, nobody wants to hear a neighbor’s cheers when a goal is scored before seeing it on the screen, making low-latency transport and playback indispensable. Synchronization among all viewing devices and social media feeds is also essential. The IETF recently started developing a QUIC-based low-latency delivery solution for media ingest and distribution. The Media-over-QUIC (MOQ) work is still under development but could be a game-changer. In this talk, we will discuss the architectural design issues and present some preliminary results.


Ali C. Begen is currently a computer science professor at Ozyegin University and a technical consultant in Comcast's Advanced Technology and Standards Group. Previously, he was a research and development engineer at Cisco. Begen received his PhD in electrical and computer engineering from Georgia Tech in 2006. To date, he received several academic and industry awards (including an Emmy® Award for Technology and Engineering), and was granted 40+ US patents. In 2020 and 2021, he was listed among the world's most influential scientists in the subfield of networking and telecommunications. More details are at

Call for papers:

We seek unpublished high-quality papers within, but not limited to, the following topics:

  • Efficient low-latency multimedia compression
  • Optimization and control mechanisms for low-latency adaptive streaming
  • Error correction for multimedia content delivery
  • Quality of experience for low-latency multimedia delivery
  • Non-standard transmission techniques (joint source-channel coding, linear video coding)
  • Latency compensation techniques
  • Generative AI-based solutions
  • Channel/network models and simulation environments for ultra-low latency delivery
  • Low-latency related standardization activities
  • Applications (AR/VR, remote control, telemedicine, etc.)
Important dates
Paper submission due March 23, 2024 March 31, 2024
Decision notification April 21, 2024
Camera ready submission April 28, 2024
Paper Submission

Full-length papers of 6 pages in length reporting on original research are solicited. The reviewing is double blind.

To submit a paper, go to the following link:, and select the track ICME2024-Workshop-ULLRMD. For detailed instructions, see