Fourth IEEE Workshop on Coding for Machines

(Joint workshop with Visual Coding for Intelligence)
September 2026, Tampere, Finland

Satellite Workshop at IEEE ICIP 2026

Workshop scope

Multimedia signals such as images, video, audio, and 3D data have traditionally been compressed for human perception. However, with the rapid growth of edge AI, multimodal large models, autonomous systems, and next-generation wireless networks enabling large-scale machine-to-machine (M2M) communication, multimedia data is increasingly consumed by machines rather than humans.

This shift calls for a rethinking of conventional compression pipelines. Instead of optimizing solely for perceptual quality and bitrate, coding methods must account for downstream machine tasks such as detection, segmentation, tracking, recognition, reasoning, and multimodal understanding—while operating under constraints of bandwidth, latency, complexity, energy, privacy, and robustness.

This workshop brings together researchers from compression, computer vision, multimodal learning, and communication systems to explore algorithms, representations, systems, and standards for efficient multimedia coding optimized for machine intelligence, as well as joint human–machine use.

Topics of Interest

We welcome high-quality, unpublished contributions including (but not limited to):

Theories and frameworks for coding for machines
Task-aware rate–distortion–complexity optimization
Joint compression and downstream task training
Coding for multiple machine tasks and human–machine use
Feature, latent, and token compression for vision and multimodal models
Coding for Large Vision-Language and Multimodal Models
Compressed-domain multimedia analysis and processing
3D coding for machine perception
Real-time edge analytics and M2M communication systems
Software–hardware co-design for efficient deployment
Datasets and benchmarking for coding for machines
Error resilience, robustness, privacy, and security in machine-oriented coding

Important dates

Paper submission: 13 May 2026

Acceptance notification: 10 June 2026

Camera-ready papers: 1 July 2026

Author Registration: 16 July 2026

Workshop date : 13 Sept. 2026
(Full-day)

Submit a paper

!!IMPORTANT!!
CfM workshop paper format follows the same format as ICIP'26 main track papers.

Reviewing of regular, special-session, and satellite-workshop papers for ICIP 2026 will be Double-Blind. Authors will need to prepare two versions of the submission: an ANONYMISED (BLIND without author names) version for reviewing, and a PUBLISH-READY (with author names) version with authors and all author details listed as demonstrated in the manuscript template.

Submission may be up to 5 pages in length for technical content (including figures, tables, references), with an optional 6th page containing references only.

Workshop papers will undergo a double-bline review process. Please refer to the ICIP main track submission guidlines for further details on the double-blind policy.

Keynote Lecture

Coding for Machines in the Era of Large Models: Advances, Challenges, and Opportunities

Coding for machines (CfM) is entering a new stage with the rise of foundation models and large multimodal models. Unlike conventional CfM pipelines, where extracted features are typically designed for specific downstream tasks, large models produce more general and reusable features that support a wide range of machine intelligence applications. This evolution fundamentally reshapes the objectives, methodologies, and system requirements of the CfM paradigm. This talk will first review recent progress in feature coding, highlighting how the field is evolving from small-scale models to large-scale models. It will then introduce the fundamental challenges arising from this shift, including feature diversity, cross-model and cross-task generalization, and semantic fidelity preservation. Finally, the talk will discuss promising future directions, such as large-model feature coding standardization, semantic distortion modeling, and more efficient machine-native visual communication systems.

Prof. Dong Liu

University of Science and Technology of China (USTC)

Dong Liu received the B.S. and Ph.D. degrees in electrical engineering from the University of Science and Technology of China (USTC), Hefei, China, in 2004 and 2009, respectively. He was a Member of Research Staff with Nokia Research Center, Beijing, China, from 2009 to 2012. He has been a faculty member at USTC since 2012 and currently holds the position of full professor. His research interests include image and video compression/coding and visual intelligence. He has authored or co-authored more than 300 papers in international journals and conferences, which were cited more than 26,000 times according to Google Scholar (h-index is 60). He has more than 40 granted patents, and dozens of technical proposals adopted by standardization groups. He received 2009 IEEE TCSVT Best Paper Award. He and his students were winners of several technical challenges held in CVPR 2025, ICIP 2024, ISCAS 2023, etc. He is a Senior Member of IEEE, CCF, and CSIG, an elected member of IVMSP-TC of IEEE SP Society, an elected member of MSA-TC of IEEE CAS Society, and an elected member of Multimedia TC of CSIG. He serves or had served as the Chair of IEEE 1857.11 Standard Sub-Working-Group (received the IEEE SA Emerging Technology Award in 2025), an Associate Editor for IEEE TIP, a Guest Editor for IEEE TCSVT, and a TPC co-chair for ICME 2026.

Invited Lecture

Bridging AI, Standards, and Industrial Deployment in Coding for Machines

As intelligent machines become increasingly capable, coding for machines is gaining strategic importance for industrial AI systems and machine‑to‑machine communication. This talk presents an industry perspective on coding for machines, discussing practical requirements such as low complexity, low latency, robustness, and standardization readiness. Ongoing MPEG activities relevant to this field—including JVET, Video Coding for Machines (VCM), Feature Coding for Machines (FCM), and Neural Network Coding (NNC)—are reviewed. Recent advances enabling faster industrial adoption, such as lightweight and efficient coding tools, are highlighted. The talk concludes with an outlook on future AI‑based coding technologies for scalable and efficient machine communication

Dr. Honglei Zhang

Nokia

Honglei Zhang is a Principal Researcher in machine learning at Nokia, Finland, where he leads research and standardization activities in AI‑based coding. He received his Bachelor’s and Master’s degrees in Electrical Engineering from Harbin Institute of Technology, China, in 1994 and 1996, respectively. With a career spanning both China and Finland, Honglei has held key roles in software engineering and system architecture at Nokia Oy Finland from 1999 to 2013. He later transitioned to academia and earned his Ph.D. in Signal Processing from Tampere University, Finland, in 2019. Honglei has authored over 50 scientific publications and is an inventor of more than 70 patents, with research interests including image and video compression, graph data analysis, and artificial intelligence. He is a recipient of Nokia’s Outstanding Inventor Awards from 2021 to 2024 and currently serves as an Associate Editor of IEEE Transactions on Circuits and Systems for Video Technology (TCSVT). His current research focuses on neural network‑based video coding for both human‑ and machine‑centric applications.

Joint Organizers

Changsheng Gao, Nanyang Technological University, Singapore

Ying Liu, Santa Clara University, USA

Heming Sun, Yokohama National University, Japan

Hyomin Choi, InterDigital, USA

Dandan Ding, Hangzhou Normal University, China

Fengqing Maggie Zhu, Purdue University, USA

Zhan Ma, Nanjing University, China

Ivan V. Bajić, Simon Fraser University, Canada

Zhu Li, University of Missouri, USA

Lu Yu, Zhejiang University, China

Technical Program Committee (confirmed)

João Ascenso, Instituto Superior Técnico

Nikolaos Thomos, University of Essex

Saeed Ranjbar Alvar, Huawei

Shiqi Wang, City University of Hong Kong

Li Zhang, ByteDance

Balu Adsumilli, Google/YouTube

Nilesh Ahuja, Intel

Hui Yuan, Shandong University

Yiyi Liao, Zhejiang University

Haoji Hu, Zhejiang University

Ming Lu, Nanjing University

Tong Chen, Nanjing University

Hao Chen, Nanjing University

Wei Zhang, Xidian University

Page updated

Google Sites

Report abuse