The PBVS 2025 Multi-modal Aerial View Image Challenge – C invites researchers and practitioners to advance automated target recognition (ATR) by leveraging multi-modal aerial imagery. This competition focuses on the classification of synthetic aperture radar (SAR) data, utilizing both SAR and electro-optical (EO) inputs to explore how multi-modal information can enhance performance in challenging conditions.

Challenge Overview

Participants will develop a classification system to predict the class label of SAR imagery, distinguishing between 10 target classes and detecting out-of-distribution (OOD) targets. Innovative approaches such as domain adaptation, transfer learning, and fusion techniques are encouraged. Submissions will be evaluated on accuracy, novelty, and creativity, with top solutions invited for further recognition.

Key Dates

• 2025.01.19: Release of training data (inputs/outputs) and validation data (inputs only).
• 2025.01.21: Validation server opens.
• 2025.02.21: Final test data release (inputs only).
• 2025.03.02: Deadline for test results, fact sheets, and code submissions.
• 2025.03.04: Preliminary results and paper submission deadline.
• 2025.06.11: PBVS Workshop at CVPR 2025, results, and award ceremony.

Awards and Opportunities

Prizes will be awarded to the top three participants, and winners will be invited to submit their solutions as papers for presentation at the 21st IEEE Workshop on Perception Beyond the Visible Spectrum (PBVS), held in conjunction with CVPR 2025.

Submission Guidelines

Participants are required to submit a description of their methodology alongside their results. Submissions will be reviewed for accuracy, reproducibility, and adherence to guidelines. Code and fact sheets must also be submitted for transparency and evaluation.

Resources

• Scripts for reproducibility and performance evaluation will be provided.
• A forum and direct email support (Justice Wheelwright: mavoc.pbvs@gmail.com) are available for queries.

For additional details, visit the competition page: PBVS 2025 Challenge.

This is an excellent opportunity to contribute to cutting-edge research in multi-modal ATR systems while gaining global recognition. We look forward to your participation.

==================================================================

21st International Conference on Content-based Multimedia Indexing, CBMI 2025
Dublin, Ireland, October 22-24, 2025

https://www.cbmi2025.org/

==================================================================

Important Dates

Regular and Special Session Papers

·         Paper deadline: April 23, 2025 (AoE)

·         Paper notification: July 1, 2025 (AoE)

·         Camera-ready and registration due: August 1, 2025 (AoE)

Demonstration Papers

·         Paper deadline: June 1, 2025 (AoE)

·         Paper notification: July 1, 2025 (AoE)

·         Camera-ready due: August 1, 2025 (AoE)

Special Session Proposals

·         Special Session proposal deadline: February 10, 2025 (AoE) February 17, 2025 (AoE)

Call for Special Sessions Proposals

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 17 February 2025 (deadline already extended). 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..).

Call for Regular Papers

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.

Call for Demonstrations

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

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