ImageCLEF 2025: Multimedia Retrieval in Medical, Social Media and Content Recommendation Applications

Bogdan Ionescu, Henning Müller, Dan-Cristian Stanciu, Ahmad Idrissi-Yaghir, Ahmedkhan Radzhabov, Alba García Seco de Herrera, Alexandra Andrei, Andrea M. Storås, Asma Ben Abacha, Benjamin Bracke, Benjamin Lecouteux, Benno Stein, Cécile Macaire, Christoph M. Friedrich, Cynthia Sabrina Schmidt, Diandra Fabre, Didier Schwab, Dimitar Dimitrov, Emmanuelle Esperança-Rodier, Mihai Gabriel Constantin et al. (27 additional authors not shown)

Abstract: ImageCLEF has been a part of CLEF (Conference and Labs of the Evaluation Forum) for more than 20 years. Started in 2003, ImageCLEF is an evaluation initiative which promotes the evaluation of technologies for annotation, indexing, retrieval, or generation of multimodal data. It provides access to large amounts of challenging data in very diverse use cases like medicine, argumentation, reasoning, generation, or content recommendation. In its 23rd edition, ImageCLEF will have four main tasks: (i) a Medical task involving concept detection and caption prediction in radiology images, synthetic medical images created with Generative Adversarial Networks (GANs), Visual Question Answering for improving the diagnosis and classification of real medical gastrointestinal images, and multimodal dermatology response generation, (ii) a joint ImageCLEF-Touché task Image Retrieval/Generation for Arguments to convey the premise of an argument, (iii) the ToPicto task which involves converting either text or speech into a meaningful sequence of pictograms and (iv) a new Multimodal Reasoning task addressing question answering and reasoning generation. In its last edition in 2024, 90 users and 31 unique teams submitted runs, totaling 257 runs, revealing a good impact in the community, similar to previous years.