Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Chamara Kasun Liyanaarachchi Lekamalage"'
Publikováno v:
Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery ISBN: 9783031207372
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cc7fb0ae3e88ccfc5cf8e4c352baec4d
https://doi.org/10.1007/978-3-031-20738-9_17
https://doi.org/10.1007/978-3-031-20738-9_17
Autor:
Chamara Kasun Liyanaarachchi Lekamalage, Zhiping Lin, Guang-Bin Huang, Jagath Chandana Rajapakse
Publikováno v:
2022 International Joint Conference on Neural Networks (IJCNN).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fc57aa8fabe0fa03b2769b148b7f6f77
https://doi.org/10.1109/ijcnn55064.2022.9892223
https://doi.org/10.1109/ijcnn55064.2022.9892223
Publikováno v:
Neural networks : the official journal of the International Neural Network Society. 147
The Tracking-by-segmentation framework is widely used in visual tracking to handle severe appearance change such as deformation and occlusion. Tracking-by-segmentation methods first segment the target object from the background, then use the segmenta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6905d0bd3cb8e1baf32556263f51f5d0
https://pubmed.ncbi.nlm.nih.gov/35042155
https://pubmed.ncbi.nlm.nih.gov/35042155
Publikováno v:
Pattern Recognition. 77:126-139
Adaptive graph learning methods for clustering, which adjust a data similarity matrix while taking into account its clustering capability, have drawn increasing attention in recent years due to their promising clustering performance. Existing adaptiv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::120ef0c9255da4ebe500b14409477a90
https://doi.org/10.1016/j.patcog.2017.12.001
https://doi.org/10.1016/j.patcog.2017.12.001
Publikováno v:
Neurocomputing. 277:78-88
Clustering generic data, i.e., data not specific to a particular field, is a challenging problem due to their diverse complex structures in the original feature space. Traditional approaches address this problem by complementing clustering with featu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::75d7a4ae972b1739bea5c13d99c59498
https://doi.org/10.1016/j.neucom.2017.01.115
https://doi.org/10.1016/j.neucom.2017.01.115
Publikováno v:
ICIP
Fully connected multi layer neural networks such as Deep Boltzmann Machines (DBM) performs better than fully connected single layer neural networks in image classification tasks and has a smaller number of hidden layer neurons than Extreme Learning M
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::715e8eeff19f517bd63b2c36a62e796a
https://doi.org/10.1109/icip.2017.8296491
https://doi.org/10.1109/icip.2017.8296491
Publikováno v:
Proceedings of ELM-2014 Volume 1 ISBN: 9783319140629
Extreme Learning Machine (ELM) is originally introduced for regression and classification. This paper extends ELM for clustering using Extreme Learning Machine Auto Encoder (ELM-AE) which learn key features of the input data. The embedding created by
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f1dc7a70dc9ebeb992b3039751ea3e56
https://doi.org/10.1007/978-3-319-14063-6_36
https://doi.org/10.1007/978-3-319-14063-6_36