Call For Participation: ImageCLEF 2026: Multimodal Challenges in Medicine, Science, Agritech, and Security

[Apologies for multiple postings]

ImageCLEF 2026: Multimodal Challenges in Medicine, Science, Agritech, and=
 Security
http://www.imageclef.org/2026/


***CALL FOR PARTICIPATION***

ImageCLEF 2026 is an evaluation campaign that is being organized as part =
of the CLEF (Conference and Labs of the Evaluation Forum) labs. The campa=
ign offers several research tasks that welcome participation from teams a=
round the world.

The results of the campaign appear in the working notes proceedings, publ=
ished by CEUR Workshop Proceedings (CEUR-WS.org) and are presented in the=
 CLEF conference. Selected contributions among the participants, will be =
invited for publication in the following year in the Springer Lecture Not=
es in Computer Science (LNCS) together with the annual lab overviews.

Target communities involve (but are not limited to): information retrieva=
l (text, vision, audio, multimedia, social media, sensor data, etc.), mac=
hine learning, deep learning, data mining, natural language processing, i=
mage and video processing, computer vision, with special attention to the=
 challenges of multi-modality, multi-linguality, and data generation.

***2026 Tasks***

ImageCLEFmedical Caption: Concept Detection, Caption Prediction and Expla=
inability in Radiology images
ImageCLEFmedical Visual Question Answering for Gastrointestinal (GI) Imag=
ing
ImageCLEFmedical GANs: Evaluation of Quality and Privacy in Synthetic Med=
ical Images Created via GANs
ImageCLEFmedical MEDIQA-CORE: Multimodal Reasoning & Reconciliation in Ra=
diology,
ImageCLEF ToPicto: Text-to-Pictogram Translation and Pictogram Prediction=

ImageCLEF Multimodal Reasoning: Multi-domain, Multi-language Viaual Quest=
ion Answering
ImageCLEF Ai4Agriculture: AI in Agriculture, Agriculture Potential Estima=
tion, Crop Identification
ImageCLEF Deepfake: Few-Shot Deepfake Generation and Deepfake Detection i=
n Images and Audio


#ImageCLEFmedical Caption (10th edition)
https://www.imageclef.org/2026/medical/caption

Interpreting and summarizing the insights gained from medical images such=
 as radiology output is a time-consuming task that involves highly traine=
d experts and often represents a bottleneck in clinical diagnosis pipelin=
es. The Automatic Image Captioning task is split into 2 subtasks: Concept=
 Detection Task, based on identifying the presence and location of releva=
nt concepts in a large corpus of medical images and the Caption Predictio=
n Task, where participating systems are tasked with composing coherent ca=
ptions for the entirety of an image.


#ImageCLEFmedical Visual Question Answering (4th edition)
https://www.imageclef.org/2026/medical/medvqa-gi

The 4th MEDVQA-GI challenge advances Visual Question Answering (VQA) for =
gastrointestinal (GI) imaging with a continued emphasis on explainability=
, clinical safety, and multimodal reasoning. The first subtask focuses on=
 developing models to accurately answer clinically relevant questions fro=
m GI endoscopy images, while the second subtask focuses on explainability=
 through multimodal justifications, that combine textual and visual evide=
nce aligned with medical reasoning.


#ImageCLEFmedical GANs (4th edition)
https://www.imageclef.org/2026/medical/gans

ImageCLEFmedical-GANs 2026 evaluates the quality and privacy of synthetic=
 tuberculosis CT images, with a new generation task requiring participant=
s to produce images while analyzing risks of patient re-identification an=
d data leakage.


#ImageCLEFmedical MEDIQA-CORE (1st edition)
https://www.imageclef.org/2026/medical/mediqa-core

The new MEDIQA-CORE 2026 task focuses on multimodal reasoning in radiolog=
y, evaluating models on tumor diagnosis using images and reports and on d=
etecting and reconciling discrepancies between conflicting radiology inte=
rpretations.


#ImageCLEF ToPicto (3rd edition)
https://www.imageclef.org/2026/topicto

ImageCLEFtoPicto 2026 aims to advance research on automatically convertin=
g written English text into meaningful sequences of pictograms to support=
 alternative and augmentative communication. The challenge introduces an =
English text-to-pictogram translation task using aligned text and pictogr=
am data, as well as a new task focused on predicting the most likely next=
 pictogram in an ongoing sequence.


#ImageCLEF Multimodal Reasoning (2nd edition)
https://www.imageclef.org/2026/multimodalreasoning

The second edition of the Multimodal Reasoning task evaluates the reasoni=
ng abilities of vision=E2=80=93language models through multilingual visua=
l question answering, expanding the multiple-choice setting and introduci=
ng open-ended questions that require generating answers directly from vis=
ual and textual content.


#ImageCLEF Ai4Agriculture (1st edition)
https://www.imageclef.org/2026/ai4agri

The AI for agriculture task includes two sub-tasks: AgriPotential, which =
evaluates models=E2=80=99 ability to estimate land suitability for differ=
ent crop types using multi-temporal and multi-spectral Sentinel-2 imagery=
 from southern France, and DACIA5, which focuses on crop identification a=
nd early crop recognition using Sentinel-1 and Sentinel-2 data over agric=
ultural parcels in Romania.


#ImageCLEF Deepfake (1st edition)
https://www.imageclef.org/2026/deepfake-detection-and-generation

The first edition of the Deepfake task evaluates both generation and dete=
ction of visual and audio deepfakes, measuring how convincingly deepfakes=
 can be created and how effectively state-of-the-art methods can detect t=
hem across multiple evaluation criteria.

*** IMPORTANT DATES ***
(may vary depending on the task)
- Run submission deadline: May 7, 2026
- Working notes submission: May 28, 2026
- CLEF 2026 conference: September 21-24, 2026, Jena, Germany

*** REGISTRATION ***
For registration, follow the instructions here: https://www.imageclef.org=
/2026, in the "Participant registration" section.


*** OVERALL COORDINATION ***
Bogdan Ionescu, Politehnica University of Bucharest, Romania
Henning M=C3=BCller, HES-SO, Sierre, Switzerland
Cristian Stanciu, Politehnica University of Bucharest, Romania


On behalf of the organizers,

Cristian Stanciu
https://www.aimultimedialab.ro/

########################################################################

To unsubscribe from the IR list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=3DIR&A=3D1

This message was issued to members of www.jiscmail.ac.uk/IR, a mailing list hosted by www.jiscmail.ac.uk, terms & conditions are available at https://www.jiscmail.ac.uk/policyandsecurity/