%0 Conference Proceedings %T Retrieving diverse social images at mediaeval 2017: Challenges, dataset and evaluation %+ Vienna University of Technology (TU Wien) %+ Laboratoire d'Analyse et Traitement d'Images (LAPI) %+ Département Intelligence Ambiante et Systèmes Interactifs (DIASI) %+ Universidade Federal de Minas Gerais = Federal University of Minas Gerais [Belo Horizonte, Brazil] (UFMG) %+ University of Applied Sciences of Western Switzerland %A Zaharieva, M. %A Ionescu, B. %A Ginsca, A.L. %A Santos, R.L.T. %A Muller, H. %Z Conference of 2017 Multimedia Benchmark Workshop, MediaEval 2017 ; Conference Date: 13 September 2017 Through 15 September 2017; Conference Code:131670 %< avec comité de lecture %B 2017 Multimedia Benchmark Workshop, MediaEval 2017 %C dublin, Iran %Y Bischke B. %Y Demarty C.-H. %Y Zaharieva M. %Y Bogdanov D. %Y Larson M. %Y Riegler M. %Y Dellandrea E. %Y Sutcliffe R. %Y Jones G.J.F. %Y Larson M. %Y Gravier G. %I CEUR-WS %V 1984 %8 2017-09-13 %D 2017 %K Evaluation metrics %K Ground truth %K Social images %K Text models %K Image retrieval %Z Engineering Sciences [physics] %Z Computer Science [cs]Conference papers %X This paper provides an overview of the Retrieving Diverse Social Images task that is organized as part of the MediaEval 2017 Benchmarking Initiative for Multimedia Evaluation. The task addresses the challenge of visual diversification of image retrieval results, where images, metadata, user tagging profiles, and content and text models are available for processing.We present the task challenges, the employed dataset and ground truth information, the required runs, and the considered evaluation metrics. %G English %L cea-01843014 %U https://cea.hal.science/cea-01843014 %~ CEA %~ DRT %~ CEA-UPSAY %~ UNIV-PARIS-SACLAY %~ CEA-UPSAY-SACLAY %~ LIST %~ GS-ENGINEERING %~ GS-COMPUTER-SCIENCE