Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Sergii, Mashtalir"'
Publikováno v:
Lecture Notes in Computational Intelligence and Decision Making ISBN: 9783030820138
The performance of artificial neural networks significantly depends on the choice of the nonlinear activation function of the neuron. Usually this choice comes down to an empirical one from a list of universal functions that have shown satisfactory r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4ef2d6e9ce562a6fa51284a95b518af9
https://doi.org/10.1007/978-3-030-82014-5_43
https://doi.org/10.1007/978-3-030-82014-5_43
Autor:
Bohdan Bilonoh, Sergii Mashtalir
Publikováno v:
2020 IEEE Third International Conference on Data Stream Mining & Processing (DSMP).
The dominant video summarization deep learning models are based on recurrent or convolutional neural network with a complex architecures. The best performing models also use attention mechanism. We propose a novel method for supervised, keyframes bas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a08b911e515dde4c51fe3fe3f6043b5a
https://doi.org/10.1109/dsmp47368.2020.9204059
https://doi.org/10.1109/dsmp47368.2020.9204059
Publikováno v:
International Journal of Intelligent Systems and Applications. 10:66-73
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2a7b647fb675d339cddd05f28cf948eb
https://doi.org/10.5815/ijisa.2018.07.07
https://doi.org/10.5815/ijisa.2018.07.07
Publikováno v:
International Journal of Intelligent Systems and Applications. 9:10-16
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::34fa33a65a116926218b3c8580018b5b
https://doi.org/10.5815/ijisa.2017.11.02
https://doi.org/10.5815/ijisa.2017.11.02
Autor:
Sergii Mashtalir
Publikováno v:
Studies in Computational Intelligence ISBN: 9783030354794
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::096db61445dc56f8781fc70bbb396627
https://doi.org/10.1007/978-3-030-35480-0
https://doi.org/10.1007/978-3-030-35480-0
Autor:
Volodymyr Mashtalir, Sergii Mashtalir
Publikováno v:
Advances in Spatio-Temporal Segmentation of Visual Data ISBN: 9783030354794
This Chapter considers approaches to video skimming into semantically-consistent segments of video streams, which are highly redundant and weakly structured data. In such a way, one of the promising ways is spatial-temporal segmentation as frame part
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::29a48b929e35ed576208adc7ec0dd278
https://doi.org/10.1007/978-3-030-35480-0_4
https://doi.org/10.1007/978-3-030-35480-0_4
Publikováno v:
Advances in Intelligent Systems and Computing ISBN: 9783030264734
ISDMCI
ISDMCI
The task of clustering is important and the most difficult part of the overall problem of Data Mining because it is based on the self-learning paradigm, i.e. implies the absence of pre-tagged training sample. In real conditions, this task is complica
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::afdf784ffe434807a63673651b85fa9f
https://doi.org/10.1007/978-3-030-26474-1_44
https://doi.org/10.1007/978-3-030-26474-1_44
Publikováno v:
Artificial Intelligence and Soft Computing ISBN: 9783030209117
ICAISC (1)
ICAISC (1)
The fuzzy clustering algorithm for high-dimensional data is proposed in this paper. An objective function which is insensitive to the “concentration of norms” phenomenon is also introduced. We recommend using a weighted parameter in the objective
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::872b149a24c5e5f0a68c7a2e51518e16
https://doi.org/10.1007/978-3-030-20912-4_36
https://doi.org/10.1007/978-3-030-20912-4_36
Publikováno v:
2018 IEEE Second International Conference on Data Stream Mining & Processing (DSMP).
In this paper the authors propose a novel technique for comparing video frame sequence presented in an arbitrary metric space. By reviewing existing best practices in spatio-temporal video segmentation and frame matching, the authors suggest mathemat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::db9299c3851fe42ae4ed1019c1384797
https://doi.org/10.1109/dsmp.2018.8478597
https://doi.org/10.1109/dsmp.2018.8478597
Publikováno v:
2018 IEEE Second International Conference on Data Stream Mining & Processing (DSMP).
Video streams as unstructured or poorly structured data issue a challenge to create a unified framework capable to depict and convey high-level stories. Up-to-date indexing and search techniques to manage video data are able to operate the voluminous
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2dff084a5976f204d3be3a26e02fa5e2
https://doi.org/10.1109/dsmp.2018.8478493
https://doi.org/10.1109/dsmp.2018.8478493