ImageCLEF 2014

Motivation

ImageCLEF 2014 is part of the CLEF 2014 to be held in the city of Sheffield in the United Kingdom. It will organize the four main tasks to benchmark the challenging task of image annotation for a wide range of source images and annotation objective, such as general multi-domain images for object or concept detection, as well as domain-specific tasks such as visual-depth images for robot vision and volumetric medical images for automated structured reporting. The tasks address different aspects of the annotation problem and are aimed at supporting and promoting the cutting-edge research addressing the key challenges in the field, such as multi-modal image annotation, domain adaptation and ontology driven image annotation. The lab is envisioned to serve as a benchmark for the aforementioned research fields.

Schedule

Each of the tasks sets its own schedule, so please check the corresponding task webpage for specific dates. A (tentative) global schedule can be found below:

• 01.11.2013: registration opens for all ImageCLEF tasks
• 15.11.2013: development data release starts (depends on the task)
• 15.03.2014: test data release starts (depends on the task)
• 01.05.2014: deadline for submission of runs by the participants (depends on the task)
• 01.06.2014: release of processed results by the task organizers (depends on the task)
• 07.06.2014: deadline for submission of working notes papers by the participants
• 15.-18.09.2014: CLEF 2014, Sheffield, UK

Registration

Registration for ImageCLEF 2014 is open. To do so please register by completing the end user agreement. Then scan and send the completed form by email to the following two addresses: Barbara Caputo <bcaputo@idiap.ch>, Alba Garcia Seco de Herrera <alba.garcia@hevs.ch>.

You also need to register in the following system in order to access the evaluation data and collect the runs

• For people already registered in the past, you can transfer your registration details to CLEF 2014 here.
• If you have not registered in the past or you do not want to transfer your details, you can register for 2014 here.

Keeping in touch

The best way to keep in touch with ImageCLEF this year, is through following ImageCLEF on twitter and facebook. Through Twitter and Facebook we will provide updates and reminders throughout the year, the twitter name is @imageclef and the facebook page

The CLEF Conference

ImageCLEF lab and all its tasks are part of the Cross Language Evaluation Forum: CLEF 2014. CLEF 2014 consists of an independent peer-reviewed conference on a broad range of issues in the fields of multilingual and multimodal information access evaluation, and a set of benchmarking activities carried in various Tracks designed to test different aspects of mono and cross-language Information retrieval systems. More details about the conference can be found here. Also there is more information about the Clef Initiative.

ImageCLEF 2014 workshop program, September 15-16 2014

September 15
15:30 → 18:00 - Lab overviews session

• 15:30-15:48 Overview of ImageCLEF 2014 - Henning Müller
  [paper] [slides]

September 16
10:30 → 12:30 - Tasks overviews session

• 10:30-11:00 Overview of the ImageCLEF 2014 Domain Adaptation Task - Novi Patricia
  [paper] [slides]
• 11:00-11:30 Overview of the ImageCLEF 2014 Scalable Concept Image Annotation Task - Mauricio Villegas
  [paper] [slides]
• 11:30-12:00 ImageCLEF Liver CT Image Annotation Task 2014 - Henning Müller
  [paper] [slides]
• 12:00-12:30 Overview of the ImageCLEF 2014 Robot Vision Task - Mauricio Villegas
  [paper] [slides]

13:30 → 15:10 - Participants session

• 13:30-13:50 KDEVIR at ImageCLEF 2014 Scalable Concept Image Annotation Task: Ontology based Automatic Image Annotation - Masaki Aono
  [paper]
• 13:50-14:10 MIL at ImageCLEF 2014: Scalable System for Image Annotation - Atsushi Kanehira
  [paper] [slides]
• 14:10-14:30 DISA at ImageCLEF 2014: The search ‐ based solution for scalable image annotation - Michal Batko
  [paper] [slides]
• 14:30-14:50 Assembling Heterogeneous Domain Adaptation Methods for Image Classification - Boris Chidlovskii
  [paper] [slides]
• 14:50-15:10 Towards Content-Based Image Retrieval: From Computer Generated Features to Semantic Descriptions of Liver CT Scans - Assaf B. Spanier
  [paper] [slides]

16:00 → 17:00 - Closing session

• 16:00-17:00 Participant feedback and discussion on the future of ImageCLEF

The Tasks

There are 4 main tasks

• Robot Vision Addressing the problem of semantic place classification using visual and depth information including object recognition.
• Scalable Concept Image Annotation Uses only automatically obtained data for multi-concept image annotation.
• Liver CT Annotation A pilot study towards automated structured reporting, the task is computer aided automatic annotation of liver CT volumes by filling in a pre-prepared form
• Domain Adaptation The aim is to build recognition systems for the target classes by exploiting existing available resources like the ImageNet, Caltetch256, AwA databases and so on,

The Organising Committee

Overall coordination

• Barbara Caputo, University of Rome La Sapienza, caputo(replace-by-an-at)dis.uniroma1.it
• Henning Müller, University of Applied Sciences Western Switzerland in Sierre, Switzerland, henning.mueller(replace-by-an-at)hevs.ch
• Jesus Martinez-Gomez, University of Castilla-La Mancha, Albacete, Spain, jesus.martinez(replace-by-an-at)uclm.es
• Mauricio Villegas, Universidad Politécnica de Valencia, Spain, mauvilsa(replace-by-an-at)upv.es

Robot Vision

• Jesus Martinez Gomez, University of Castilla-La Mancha, Albacete, Spain, jesus.martinez(replace-by-an-at)uclm.es
• Ismael Garcia Varea, University of Castilla-La Mancha, Albacete, Spain, Ismael.Garcia(replace-by-an-at)uclm.es
• Miguel Cazorla, University of Alicante, Alicante, Spain, miguel(replace-by-an-at)dccia.ua.es
• Vicente Morell, Research Institute, University of Alicante, Alicante, Spain, vmorell(replace-by-an-at)dccia.ua.es

Scalable Concept Image Annotation

• Mauricio Villegas, Universidad Politécnica de Valencia, Spain, mauvilsa(replace-by-an-at)upv.es
• Roberto Paredes, Universidad Politécnica de Valencia, Spain, rparedes(replace-by-an-at)dsic.upv.es

Liver CT Annotation

• Burak Acar, PhD, Bogazici University, EE Dept., Istanbul, Turkey, acarbu(replace-by-an-at)boun.edu.tr
• Suzan Uskudarli, PhD, Bogazici University, CmpE Dept., Istanbul, Turkey, suzan.uskudarli(replace-by-an-at)boun.edut.tr
• Neda Marvasty,Bogazici University, EE Dept., Istanbul, Turkey, neda.barzegarmarvasti(replace-by-an-at)boun.edu.tr (Contact Person)

Domain Adaptation

• Barbara Caputo, University of Rome La Sapienza, caputo(replace-by-an-at)dis.uniroma1.it
• Novi Patricia, Idiap Research Institute, novi.patricia(replace-by-an-at)idiap.ch

Acknowledgments

The imageCLEF 2014 lab would have not been possible without the help, effort and dedication of the following people:

• Alba Garcia Seco de Herrera, University of Applied Sciences Western Switzerland in Sierre, Switzerland, alba.garcia(replace-by-an-at)hevs.ch
• Ivan Eggel, University of Applied Sciences Western Switzerland in Sierre, Switzerland, ivan.eggel(replace-by-an-at)hevs.ch
• Luca Piras, University of Cagliari, Italy, luca.piras(replace-by-an-at)unica.it
• Andrew Gilbert, University of Surrey , United Kingdom, wackygerbs(replace-by-an-at)gmail.com