Automatic detection of passable roads after floods in remote sensed and social media data

Autor: Ahmad, Kashif, Pogorelov, Konstantin, Riegler, Michael, Ostroukhova, Olga, Halvorsen, Paal, Conci, Nicola, Dahyot, Rozenn

This paper addresses the problem of floods classification and floods aftermath detection utilizing both social media and satellite imagery. Automatic detection of disasters such as floods is still a very challenging task. The focus lies on identifyin

Externí odkaz: http://arxiv.org/abs/1901.03298

Medico multimedia task at MediaEval 2018

Autor: Pogorelov, Konstantin, Riegler, Michael, Halvorsen, Pål, Hicks, Steven, Randel, Kristin Ranheim, Dang Nguyen, Duc Tien, Lux, Mathias, Ostroukhova, Olga, de Lange, Thomas

Publikováno v: CEUR Workshop Proceedings

The Medico: Multimedia for Medicine Task, running for the second time as part of MediaEval 2018, focuses on detecting abnormalities, diseases, anatomical landmarks and other findings in images captured by medical devices in the gastrointestinal tract

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::6dd6477b2b61067ed437c3774b2778b3
https://hdl.handle.net/1956/20930

Deep learning and hand-crafted feature based approaches for polyp detection in medical videos

Autor: Pogorelov, Konstantin, Ostroukhova, Olga, Jeppsson, Mattis, Espeland, Håvard, Griwodz, Carsten, de Lange, Thomas, Riegler, Michael, Halvorsen, Pål

Publikováno v: Pogorelov, K., Ostroukhova, O., Jeppsson, M., Espeland, H., Griwodz, C., de Lange, T., ... Halvorsen, P. (2018). Deep learning and hand-crafted feature based approaches for polyp detection in medical videos. IEEE International Symposium on Computer-Based Medical Systems, 2018, 381-386.

Externí odkaz: https://hdl.handle.net/10037/14626

A comparison of deep learning with global features for gastrointestinal disease detection

Autor: Pogorelov, Konstantin, Riegler, Michael, Halvorsen, Pål, Griwodz, Carsten, de Lange, Thomas, Randel, Kristin, Eskeland, Sigrun, Dang-Nguyen, Duc-Tien, Ostroukhova, Olga, Lux, Mathias, Spampinato, Concetto

Publikováno v: Pogorelov, Konstantin, Riegler, Michael, Halvorsen, Pål, Griwodz, Carsten, de Lange, Thomas, Randel, Kristin, Eskeland, Sigrun, Dang-Nguyen, Duc-Tien ORCID: 0000-0002-2761-2213 , Ostroukhova, Olga, Lux, Mathias and Spampinato, Concetto (2017) A comparison of deep learning with global features for gastrointestinal disease detection. In: MediaEval 2017 Multimedia Benchmark Workshop, 13-16 Sept 2017, Dublin, Ireland.

This paper presents our approach for the 2017 Multimedia for Medicine Medico Task of the MediaEval 2017 Benchmark. We pro- pose a system based on global features and deep neural networks, and preliminary results comparing the approaches are presented

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_______119::85b6ed987d6e6f52869e583e7bf4a33e
http://doras.dcu.ie/22033/