Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Georgios Evangelopoulos"'
Autor:
Athanasia Zlatintsi, Petros Koutras, Georgios Evangelopoulos, Nikolaos Malandrakis, Niki Efthymiou, Katerina Pastra, Alexandros Potamianos, Petros Maragos
Publikováno v:
EURASIP Journal on Image and Video Processing, Vol 2017, Iss 1, Pp 1-24 (2017)
Abstract Research related to computational modeling for machine-based understanding requires ground truth data for training, content analysis, and evaluation. In this paper, we present a multimodal video database, namely COGNIMUSE, annotated with sen
Externí odkaz:
https://doaj.org/article/8227720ba6b24450ae51c338d8c28908
Autor:
Georgios Evangelopoulos
Στόχος της διατριβής είναι η ανάδειξη και ανάλυση μικροδομών της οπτικής υφής, για την εφαρμογή αποδοτικών μοντέλων, την εξαγωγή περιγρ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6ba3ccea71e2ae9e407d8a3fcbf17b3f
https://doi.org/10.12681/eadd/16931
https://doi.org/10.12681/eadd/16931
Publikováno v:
Pattern Recognition. 86:201-208
In this paper, we propose the use of data symmetries, in the sense of equivalences under signal transformations, as priors for learning symmetry-adapted data representations, i.e., representations that are equivariant to these transformations. We rel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b84b1b320fa156e3b43f9c934aeacae8
https://doi.org/10.1016/j.patcog.2018.07.025
https://doi.org/10.1016/j.patcog.2018.07.025
Autor:
George Toderici, G. Passalis, Dat Chu, Ioannis A. Kakadiaris, Shishir K. Shah, Georgios Evangelopoulos, Xi Zhao, Theoharis Theoharis
Publikováno v:
Computer Vision and Image Understanding. 154:137-151
Describes a conceptual framework for 3D-2D (or 2D-3D) face recognition.Proposes a novel 3D-2D system for 2D image face recognition from 3D datasets.Proposes a method to build subject-specific 3D gallery models, using 3D+2D data, and a method for mode
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5b3839445e491d90532dc04d2edb21e
https://doi.org/10.1016/j.cviu.2016.04.012
https://doi.org/10.1016/j.cviu.2016.04.012
Publikováno v:
IEEE Transactions on Cybernetics. 44:725-736
Asymmetric 3D to 2D face recognition has gained attention from the research community since the real-world application of 3D to 3D recognition is limited by the unavailability of inexpensive 3D data acquisition equipment. A 3D to 2D face recognition
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fca77cc6f26682e4c1c93ac83d79f370
https://doi.org/10.1109/tcyb.2013.2291196
https://doi.org/10.1109/tcyb.2013.2291196
Multimodal Saliency and Fusion for Movie Summarization Based on Aural, Visual, and Textual Attention
Autor:
Georgios Skoumas, Petros Maragos, Alexandros Potamianos, Georgios Evangelopoulos, Yannis Avrithis, Athanasia Zlatintsi, Konstantinos Rapantzikos
Publikováno v:
IEEE Transactions on Multimedia
Multimodal streams of sensory information are naturally parsed and integrated by humans using signal-level feature extraction and higher level cognitive processes. Detection of attention-invoking audiovisual segments is formulated in this work on the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f91729342e62483424823c32ba6a9e36
https://doi.org/10.1109/tmm.2013.2267205
https://doi.org/10.1109/tmm.2013.2267205
AimsBladder dysfunction is frequent during the course of multiple sclerosis (MS), observed in up to 75% of patients. Urinary symptomatology can be a feature of the first episode of MS in a minority of cases, and most often shows characteristics of an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______2127::43fba290122bc35b86b2a8b209c970b9
https://pergamos.lib.uoa.gr/uoa/dl/object/uoadl:3171867
https://pergamos.lib.uoa.gr/uoa/dl/object/uoadl:3171867
Publikováno v:
IEEE Transactions on Audio, Speech and Language Processing. 14:2024-2038
The ability to accurately locate the boundaries of speech activity is an important attribute of any modern speech recognition, processing, or transmission system. The effort in this paper is the development of efficient, sophisticated features for sp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ed688f035bd9241e5873949308c6ce7b
https://doi.org/10.1109/tasl.2006.872625
https://doi.org/10.1109/tasl.2006.872625
Publikováno v:
IEEE Geoscience and Remote Sensing Letters. 2:394-398
Automated processing of digitized soilsection images reveals elements of soil structure and draws primary estimates of bioecological importance, like ground fertility and changes in terrestrial ecosystems. We examine a sophisticated integration of so
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c47c048f00a32fefea6ba0e44eea9c75
https://doi.org/10.1109/lgrs.2005.851752
https://doi.org/10.1109/lgrs.2005.851752
Publikováno v:
INTERSPEECH
Scopus-Elsevier
Scopus-Elsevier
Extracting discriminant, transformation-invariant features from raw audio signals remains a serious challenge for speech recognition. The issue of speaker variability is central to this problem, as changes in accent, dialect, gender, and age alter th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::857a8ebfc21afdefae0e8efbbd9ddf43
https://doi.org/10.21437/interspeech.2014-518
https://doi.org/10.21437/interspeech.2014-518