Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Christos Veinidis"'
Publikováno v:
Journal of Imaging, Vol 9, Iss 9, p 189 (2023)
3D reconstruction of fishes provides the capability of extracting geometric measurements, which are valuable in the field of Aquaculture. In this paper, a novel method for 3D reconstruction of fishes using the Coded Structured Light technique is pres
Externí odkaz:
https://doaj.org/article/88a2b34b60a84612ae6347ee8accad65
Publikováno v:
The Visual Computer. 37:1309-1326
We propose and experimentally investigate the usefulness of several features for selecting image content (objects) suitable for image captioning. The approach taken explores three broad categories of features, namely geometric, conceptual, and visual
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::54464d6cc0cd3526fe54329ae50afc28
https://doi.org/10.1007/s00371-020-01867-9
https://doi.org/10.1007/s00371-020-01867-9
Publikováno v:
2789–2814
Multimedia tools and applications
Multimedia tools and applications
The problem of human action retrieval based on the representation of the human body as a 3D mesh is addressed. The proposed 3D mesh sequence descriptor is based on a set of trajectories of salient points of the human body: its centroid and its five p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b07000d3d95afd0c8075d4f417fa580d
https://doi.org/10.1007/s11042-018-5855-2
https://doi.org/10.1007/s11042-018-5855-2
Publikováno v:
Multimedia Tools and Applications. 76:2059-2085
In this paper, the problem of unsupervised human action retrieval in 3D mesh sequences is addressed. An action is composed of a mesh sequence, wherein each frame is represented by a static shape descriptor. Six state-of-the-art static descriptors are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6aed55b0d63014b3eef7ebb8a8cf5203
https://doi.org/10.1007/s11042-015-3137-9
https://doi.org/10.1007/s11042-015-3137-9
Publikováno v:
International Journal of Image and Graphics. 19:1950018
Two novel methods for fully unsupervised human action retrieval using 3D mesh sequences are presented. The first achieves high accuracy but is suitable for sequences consisting of clean meshes, such as artificial sequences or highly post-processed re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a0007ee7359402a554747706478f3125
https://doi.org/10.1142/s0219467819500189
https://doi.org/10.1142/s0219467819500189
Publikováno v:
Journal of Imaging; Sep2023, Vol. 9 Issue 9, p189, 21p
Publikováno v:
Visual Computer; Jun2021, Vol. 37 Issue 6, p1309-1326, 18p
Publikováno v:
International Journal of Image & Graphics; Jul2019, Vol. 19 Issue 3, pN.PAG-N.PAG, 34p
Publikováno v:
Multimedia Tools & Applications; Feb2019, Vol. 78 Issue 3, p2789-2814, 26p
Publikováno v:
Multimedia Tools & Applications; Jan2017, Vol. 76 Issue 2, p2059-2085, 27p