DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ntalianis, Klimis | - |
dc.contributor.author | Doulamis, Anastasios | - |
dc.contributor.author | Kollias, Stefanos | - |
dc.contributor.author | Doulamis, Nikolaos | - |
dc.date.accessioned | 2024-10-31T14:54:43Z | - |
dc.date.available | 2024-10-31T14:54:43Z | - |
dc.date.issued | 2002-01-01 | - |
dc.identifier | scopus-70450198494 | - |
dc.identifier.isbn | 978-3-540-46084-8 | - |
dc.identifier.isbn | 978-3-540-44074-1 | - |
dc.identifier.issn | 1611-3349 | - |
dc.identifier.other | 70450198494 | - |
dc.identifier.uri | https://uniwacris.uniwa.gr/handle/3000/2853 | - |
dc.description.abstract | In this paper efficient performance generalization of neural network classifiers is accomplished, for unsupervised video object segmentation in videoconference/videophone sequences. Each time conditions change, a retraining phase is activated and the neural network classifier is adapted to the new environment. During retraining both the former and current knowledge are utilized so that good network generalization is achieved. The retraining algorithm results in the minimization of a convex function subject to linear constraints, leading to very fast network weight adaptation. Current knowledge is unsupervisedly extracted using a face-body detector, based on Gaussian p.d.f models. A binary template matching technique is also incorporated, which imposes shape constraints to candidate face regions. Finally the retrained network performs video object segmentation to the new environment. Several experiments on real sequences indicate the promising performance of the proposed adaptive neural network as efficient video object segmentation tool. | en_US |
dc.language.iso | en | en_US |
dc.relation.ispartof | Artificial Neural Networks - ICANN 2002 | en_US |
dc.relation.ispartofseries | Lecture Notes in Computer Science | en_US |
dc.title | Neural networks retraining for unsupervised video object segmentation of videoconference sequences | en_US |
dc.type | Conference Paper | en_US |
dc.relation.conference | International Conference on Artificial Neural Networks (ICANN 2002), 28-30 August 2002, Madrid, Spain | en_US |
dc.identifier.doi | 10.1007/3-540-46084-5_212 | en_US |
dc.identifier.scopus | 2-s2.0-70450198494 | - |
dcterms.accessRights | 0 | en_US |
dc.relation.dept | Department of Business Administration | en_US |
dc.relation.faculty | School of Administrative, Economics and Social Sciences | en_US |
dc.identifier.spage | 1312 | en_US |
dc.identifier.epage | 1318 | en_US |
dc.collaboration | University of West Attica (UNIWA) | en_US |
dc.journals | Open Access | en_US |
dc.publication | Peer Reviewed | en_US |
dc.country | Greece | en_US |
local.metadatastatus | not verified | en_US |
item.cerifentitytype | Publications | - |
item.languageiso639-1 | en | - |
item.openairetype | Conference Paper | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.fulltext | No Fulltext | - |
item.grantfulltext | none | - |
crisitem.author.dept | Department of Business Administration | - |
crisitem.author.faculty | School of Administrative, Economics and Social Sciences | - |
crisitem.author.parentorg | School of Administrative, Economics and Social Sciences | - |
Appears in Collections: | Book Chapter / Κεφάλαιο Βιβλίου |
CORE Recommender
SCOPUSTM
Citations
2
checked on Nov 1, 2024
Page view(s)
7
checked on Nov 5, 2024
Google ScholarTM
Check
Altmetric
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.