Wassim El Ahmar, Ph.D., P.Eng.
Professor – Long Term Appointment
School of Electrical Engineering and Computer Science
800 King Edward, SITE 4063, Ottawa, Ontario, Canada
Université d'Ottawa | University of Ottawa
January 21st, 2025
Daniela Lopez de Luise Wassim El Ahmar, Ph.D., P.Eng.
Professor – Long Term Appointment
School of Electrical Engineering and Computer Science
800 King Edward, SITE 4063, Ottawa, Ontario, Canada
Université d'Ottawa | University of Ottawa
January 21st, 2025
Daniela Lopez de Luise ==================================================================
21st International Conference on Content-based Multimedia Indexing, CBMI 2025 Dublin, Ireland, October 22-24, 2025
==================================================================
Paper deadline: April 23, 2025 (AoE)
Paper notification: July 1, 2025 (AoE)
Camera-ready and registration due: August 1, 2025 (AoE)
Paper deadline: June 1, 2025 (AoE)
Paper notification: July 1, 2025 (AoE)
Camera-ready due: August 1, 2025 (AoE)
Special Session proposal deadline: February 10, 2025 (AoE)
CBMI aims at bringing together the various communities involved in all aspects of content-based multimedia indexing for retrieval, browsing, management, visualization and analytics. At this time we invite you to propose special sessions for CBMI 2025. Special sessions are dedicated conference sessions, each focusing on one state-of-the-art research direction within the content-based multimedia indexing field. Special session papers, which can be invited or submitted, will supplement the regular research papers and be included in the proceedings of CBMI 2025. All special session papers will be subject to the standard rigorous review process for CBMI.
Special session proposals must be submitted by email to the special session chairs (submissions@cbmi2025.org) using subject “CBMI 2025 Special Session Proposal” by 10 February 2025. Proposals will be evaluated based on the relevance to CBMI, qualifications of the organiser(s), and the quality and community interest of the topic/proposed potential papers. Required details for proposals are described below.
Usually, each special session should consist of four to six full-papers. In order to ensure the high quality of all conference papers, all papers submitted to special sessions at CBMI 2025 will be peer-reviewed through a standard review process. If a special session has many high-quality submissions, some of the submissions may potentially be moved to some regular sessions.
The review process will be coordinated with the regular technical program review process, as coordinated by the TPC chairs. The organisers of each special session must 2 reviews per submitted/invited paper, while the regular program committee will provide 1-2 additional reviews. Final decision on acceptance/rejection will be made in collaboration between the special session chairs and the CBMI 2025 TPC chairs.
Please include the following information in your proposal:
Title of the proposed special session.
Name, affiliation, brief biography and contact information for each of the organisers.
A session abstract including significance justification and a brief overview of the state-of-the-art of the proposed special session topic. Note: The session abstract should be in a format that can be copied directly to the conference website to advertise the session.
List of potential papers if available, including for each paper: tentative title, author list, and preferably a short abstract.
Proposal for arrangement of the reviews from session organizers (e.g., list of members of mini-PC for the special session).
Description of the session format (e.g., conventional technical talks, short talks & panel discussion, etc..).
CBMI aims at bringing together the various communities involved in all aspects of content-based multimedia indexing for retrieval, browsing, management, visualization and analytics.
The organisers of CBMI 2025 call for novel and original research papers that are addressing the various topics of interest related to the conference. We encourage contributions both on theoretical aspects and applications of CBMI in the new era of Artificial Intelligence and foundation/language-backed-backed models for multimedia for multimedia. Authors are invited to submit previously unpublished research papers highlighting significant contributions addressing these topics.
Authors can submit full papers (6 pages + references) or short papers (4 pages + references).
Submissions to CBMI are peer reviewed in a double blind process and the language of the conference is English. For full details on the submission process see the submission guidelines.
Authors of high-quality papers accepted to the conference may be invited to submit extended versions of their contributions to a special journal issue.
CBMI aims at bringing together the various communities involved in all aspects of content-based multimedia indexing for retrieval, browsing, management, visualization and analytics. We invite authors to report on novel and compelling demonstrations in all topic areas of CBMI. Demonstration papers are subject to peer review according to criteria such as novelty, interestingness, applications of or enhancements to state-of-the-art, and potential impact.
The length of the papers should be up to 4 pages. An additional 1-2 pages should be appended to the paper that illustrate how the demo will be conducted on-site at CBMI 2025. This additional content will not be published in the conference proceedings, should the submission be accepted. Including a link to a video showing the demo in action is highly encouraged. The submissions are peer-reviewed in a single-blind process. For full details on the submission process see the submission guidelines.
Presenters are expected to bring the necessary equipment (computers, etc.) themselves. The conference will provide a table, power outlet, screen, wireless (shared) internet and a poster board. If you have special needs (e.g., more space), please include a related note in your demo submission.
Topics of interest to the CBMI community include (but are not limited to) the following:
Multimedia Content Analysis and Indexing:
Media content analysis and mining
AI/ML approaches for content understanding
Multimodal and cross-modal indexing
Activity recognition and event-based multimedia indexing and retrieval
Multimedia information retrieval (image, audio, video, text)
Conversational search and question-answering systems
Multimedia recommendation
Multimodal analytics, summarization, visualization, organization and browsing of multimedia content
Multimedia verification (e.g., multimodal fact-checking, deep fake analysis)
Foundation models, large multimedia models, large language models and vision language models
Explainability in multimedia learning
Large scale multimedia database management
Evaluation and benchmarking of multimedia retrieval systems
Multimedia User Experiences:
Extended reality (AR/VR/MR) interfaces
Mobile interfaces and user interaction
Presentation and visualization tools
Affective adaptation and personalization
Relevance feedback and interactive learning
Applications of Multimedia Indexing and Retrieval:
Multimedia and sustainability
Healthcare and medical applications
Cultural heritage and entertainment applications
Educational and social applications
Egocentric, wearable and personal multimedia
Applications to forensics, surveillance and security
Environmental and urban multimedia applications
Earth observation and astrophysics
Physical and industrial processes
January 21st, 2025
Daniela Lopez de Luise The full-day workshop will provide a forum for presenting original research in computer vision and pattern recognition applied to large-scale remote sensing imagery. The focus will be on recent advancements in automatic analysis of remote sensing imagery for Earth Observation and its impact on geoscience, climate change, sustainable development goals, and the general understanding of the Earth system. A non-exhaustive list of topics of interest includes the following:
– Super-resolution in the spectral and spatial domain
– Hyperspectral and multispectral image processing
– Reconstruction and segmentation of optical and LiDAR 3D point clouds
– Feature extraction and learning from spatiotemporal data
– Analysis of UAV / aerial and satellite images and videos
– Deep learning tailored for large-scale Earth Observation
– Domain adaptation, concept drift, and the detection of out-of-distribution data
– Data-centric machine learning
– Evaluating models using unlabeled data
– Self-, weakly, and unsupervised approaches for learning with spatial data
– Foundation models and representation learning in the context of EO
– Human-in-the-loop and active learning
– Multi-resolution, multi-temporal, multi-sensor, multi-modal processing
– Fusion of machine learning and physical models
– Explainable and interpretable machine learning in Earth Observation applications
– Uncertainty quantification of machine-learning based prediction from EO data
– Applications for climate change, sustainable development goals, and geoscience
– Public benchmark datasets: training data standards, testing & evaluation metrics, as well as open-source research and development.
January 21st, 2025
Daniela Lopez de Luise
January 21st, 2025
Daniela Lopez de Luise Call for Papers – “Digital Twinning in Smart Applications”
At the International Joint Conference on Neural Networks
June 30 – July 5, 2025 Rome, Italy
Submission deadline: January 15, 2025 January 30, 2025
The advent of digital twins has revolutionized the simulation and optimization of real-world scenarios. Digital twins are comparable virtual replicas of real-world systems, assets, or processes that allow for real-time optimization, simulation, and monitoring. Through a complete or semi-complete digital replication of a physical object, they provide performance analysis, problem prediction, and scenario testing without affecting the real system. When combined with deep learning, these virtual replicas gain the ability to learn from extensive data, adapt to changing conditions, and predict future states with exceptional precision. This integration enables digital twins to not only reflect their physical counterparts but also anticipate issues, enhance performance, and autonomously support decision-making processes. The applications are extensive: in manufacturing, it leads to smart factories where production lines optimize themselves for efficiency; in healthcare, patient-specific digital twins can forecast health trajectories and tailor treatments; in urban planning, city-wide digital twins can model traffic and energy use to improve sustainability. Deep learning allows digital twins to become dynamic entities that change in tandem with their physical counterparts, creating interesting prospects for innovation in a variety of research and application areas.
Manuscripts related to the Special Session shall be submitted through the CMT paper submission website as a regular paper (Main Track) by selecting this special session “Digital Twinning in Smart Applications” as primary Subject Area. All submitted papers will be reviewed in the same process as the regular papers. Accepted contributions will be part of the conference proceedings.
In order to prepare your submission, please follow the guidelines of the main conference at https://2025.ijcnn.org/authors/initial-author-instructions.
Special Session Co-Chairs
============================================