000002258 001__ 2258
000002258 005__ 20190423205539.0
000002258 037__ $$aCONFERENCE
000002258 245__ $$aOverview of ImageCLEFcaption 2017 :$$bimage caption prediction and concept detection for biomedical images
000002258 260__ $$aDublin, Ireland$$b11-14 September 2017$$c2017
000002258 269__ $$a2017-09
000002258 300__ $$a10 p.
000002258 506__ $$avisible
000002258 520__ $$9eng$$aThis paper presents an overview of the ImageCLEF 2017 caption tasks on the analysis of images from the biomedical literature. Two subtasks were proposed to the participants: a concept detection task and caption prediction task, both using only images as input. The two subtasks tackle the problem of providing image interpretation by extracting concepts and predicting a caption based on the visual information of an image alone. A dataset of 184,000 figure-caption pairs from the biomedical open access literature (PubMed Central) are provided as a testbed with the majority of them as trainign data and then 10,000 as validation and 10,000 as test data. Across two tasks, 11 participating groups submitted 71 runs. While the domain remains challenging and the data highly heterogeneous, we can note some surprisingly good results of the difficult task with a quality that could be beneficial for health applications by better exploiting the visual content of biomedical figures.
000002258 592__ $$aHEG-VS
000002258 592__ $$bInstitut Informatique de gestion
000002258 592__ $$cEconomie et Services
000002258 65017 $$aInformatique
000002258 6531_ $$9eng$$aImageCLEF 2017
000002258 6531_ $$9eng$$acaption prediction
000002258 6531_ $$9eng$$aimage understanding
000002258 6531_ $$9eng$$acomputer vision
000002258 6531_ $$9eng$$aradiology
000002258 655_7 $$afull paper
000002258 700__ $$aEickhoff, Carsten$$uETH Zurich, Switzerland
000002258 700__ $$aSchwall, Immanuel$$uETH Zurich, Switzerland
000002258 700__ $$aGarcía Seco de Herrera, Alba$$uLister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, USA
000002258 700__ $$aMüller, Henning$$uUniversity of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)
000002258 711__ $$aCLEF 2017 working Notes$$cDublin, Ireland$$d11/09/2017 / 14/09/2017
000002258 773__ $$tProceedings of the CLEF 2017 working notes
000002258 85641 $$uhttp://ceur-ws.org/Vol-1866/invited_paper_7.pdf$$zOnline version
000002258 8564_ $$s450484$$uhttps://hesso.tind.io/record/2258/files/M%C3%BCller_2017_CLEF2017_image_caption.pdf
000002258 8564_ $$s1490571$$uhttps://hesso.tind.io/record/2258/files/M%C3%BCller_2017_CLEF2017_image_caption.pdf?subformat=pdfa$$xpdfa
000002258 909CO $$ooai:hesso.tind.io:2258$$pDOMAINE_ECONOMIESERVICE_CONFERENCE$$pGLOBAL_SET
000002258 906__ $$aGREEN
000002258 950__ $$aI1
000002258 980__ $$aconference