It is with great pleasure that we invite you to the 2025 9th International Conference on Vision, Image and Signal Processing (ICVISP 2025), which is scheduled to take place from November 28-30, 2025, in Xi'an, China. The conference is organized by Northwestern Polytechnical University and Xi'an University of Posts & Telecommunications, and technically sponsored by Asia-Pacific Signal and Information Processing Association (APSIPA) and IEEE Xi'an Section. ICVISP is committed to delivering a platform for collaboration and discovery, with the aim of driving progress in image, vision, and signal processing—key technologies that are enhancing our understanding of the world and propelling advancements in artificial intelligence, machine learning, and a multitude of other applications that are transforming industries and improving lives. We warmly invite your contributions and eagerly anticipate the opportunity to meet with you in person at ICVISP 2025.
Registered and presented full papers will be included in the ICVISP 2025 digital conference proceedings (ISBN: 979-8-3315-5682-2), which will be published by IEEE and submitted for inclusion into IEEE Xplore subject to meeting IEEE Xplore's scope and quality requirements, and also submitted to major citation databases (including, but not limited to Ei Compendex and Scopus) for review and indexing.
![]()
Note: All accepted papers must be presented at the conference. No-show papers will be excluded from the conference proceedings.
Authors are invited to submit abstract / full paper through the online submission system: ![]()
Please click here to learn how to submit.
The manuscript should be written in English including tables, figures, equations, and algorithms. Only original papers will be considered for the conference program. The manuscripts must not be previously published nor accepted for publication elsewhere, and must not be under review by any other conference or publication during the review cycle.
Please download manuscript templates here:
![]()
Registration Due:
November 14, 2025
Final Paper Submission Due:
November 14, 2025
Main Conference:
November 28-30, 2025
1. Language Requirement: The conference exclusively accepts manuscripts written in English. All submissions must be composed entirely in English.
2. Academic Integrity: Any form of plagiarism, copying, or improper citation is strictly prohibited. All manuscripts will undergo originality screening. Submissions suspected of plagiarism or serious academic misconduct will not be sent for review and may be summarily rejected.
3. Originality and Unpublished Status: Submitted manuscripts must represent original research findings. The content must not have been published previously in any domestic or international publicly available publication (including journals, books, etc.) or presented at any other academic conference (including predecessors or related conferences of this event).
4. Manuscript Length: The length of the manuscript's main body (including figures, tables, and references) shall be no fewer than 5 pages.
5. Formatting Specifications: Manuscripts must adhere strictly to the latest official paper template
| The topics of interest include, but are not limited to: |
| Computer Vision 3D Computer Vision Deep Learning Architectures and Techniques |
| Image processing Synthesis, Rendering, & Visualization Computational Imaging |
| Signal Processing Applied Signal Processing Systems Audio & Acoustic Signal Processing |
| Multimodal AI Multimodal Representations (Language, Vision, Audio, Touch, Depth, etc.) Multimodal Data Modeling |
| Applications Augmented and Mixed Reality Autonomous Driving |
| More |
![]() |
![]() |
![]() |
||
| Prof. Kai-Kuang Ma | Prof. Tatsuya Kawahara | Prof. Toshihisa Tanaka | ||
| Fellow of the Singapore Academy of Engineering | Former President of APSIPA | Vice President of APSIPA | ||
| Nanjing University of Aeronautics and Astronautics, China | Kyoto University, Japan | Tokyo University of Agriculture and Technology, Japan | ||
| Speech Title: AI-Powered Imaging: Transforming the Future of Visual Experience | Speech Title: Making a Robot to Communicate with Social Signals | Speech Title: Decoding Internal States via Biosignals for Speech and Social Interaction |
![]() |
![]() |
![]() |
|
ICVISP 2017 | Osaka, Japan Publisher: IEEE Indexed by EI | Scopus ISBN: 978-1-5386-0612-4 |
ICVISP 2018 | Las Vegas, USA Publisher: ACM Indexed by EI | Scopus ISBN: 978-1-4503-6529-1 |
ICVISP 2019 | University of British Columbia Publisher: ACM Indexed by EI | Scopus ISBN: 978-1-4503-7625-9 |
![]() |
![]() |
![]() |
|
ICVISP 2020 | Virtually Publisher: ACM Indexed by EI | Scopus ISBN: 978-1-4503-8953-2 |
ICVISP 2021 | Virtually Publisher: IEEE Indexed by EI | Scopus ISBN: 978-1-6654-0770-0 |
ICVISP 2022 | Virtually Publisher: IOP JPCS Indexed by EI | Scopus ISSN: 1742-6596 |
![]() |
![]() ![]() |
|
|
ICVISP 2023 | Dali, China Publisher: IET Indexed by EI | Scopus ISBN: 978-1-83724-014-2 |
EEE ICVISP 2024 | Kunming, China Publisher: IEEE Indexed by EI | Scopus ISBN: 979-8-3315-4146-0 |
|

ICVISP 2025 has been successfully held during November 28-30, 2025 in Xi'an, China.
IEEE ICVISP 2024 has been successfully held during December 27-29, 2024 in Kunming, China.
ICVISP 2023 has been successfully held during November 24-26, 2023 in Dali, China.
ICVISP 2022 has been successfully held virtually during December 10-12, 2022.
ICVISP 2021 has been held virtually during December 18-20, 2021 due to the COVID-19 virus.
ICVISP 2020 has been held virtually during December 9-11, 2020 due to the COVID-19 virus.
ICVISP 2019 has been successfully held at The University of British Columbia, Vancouver Campus, Canada during August 26-28, 2019.
ICVISP 2018 has been successfully held at the University of Nevada, Las Vegas, USA during August 27-29, 2018.
ICVISP 2017 has been successfully held in Osaka, Japan during September 22-24, 2017.

Xi'an Lanxi International Hotel | 西安蓝溪国际酒店