The workshop invites original research contributions on all multimodal segmentation aspects. Topics of interest include, but are not limited to:
Foundational models for image/video/3D segmentation
Open-vocabulary/open-world image/video/3D segmentation
Semantic/instance/panoptic image/video/3D segmentation
Universal image/video/3D segmentation models
Diffusion models for segmentation
Training-free segmentation models
Real-world segmentation applications in medical imaging, autonomous driving, robotics, and visual navigation.
Submission Site: TBD
Formatting Requirements:
Papers must not exceed 6 pages, including text, figures, and references.
Workshop papers should follow the same formatting guidelines as the main conference papers. Please refer to the main conference instructions here. All submissions must adhere to the double-blind review process in accordance with the conference guidelines.
Paper Submission Due Date: 25 March 2026
Notification of Acceptance/Rejection: 25 April 2026
Camera-Ready Due Date: 15 May 2026
Jean Lahoud, MBZUAI, UAE.
Lei Huang, Beihang University, CHINA
Ashmal Vayani, University of Central Florida, USA
Munawar Hayat, Qualcomm, USA
Mustansar Fiaz, IBM, USA
Muzammal Nasser, Khalifa University, UAE
Yaxing Wang, Nankai University, CHINA
Ketan More, MBZUAI, UAE
Zongyan Han, MBZUAI, UAE
Aditya Arora, York University, CANADA
Akshita Gupta, University of Guelph, CANADA
K J Joseph, Adobe Research, INDIA
Sanath Narayan, TII, UAE
Hanoona Bangalath, MBZUAI, UAE
Sara Ghaboura, MBZUAI, UAE
Ritesh Thawkar, MBZUAI, UAE