Zobrazeno 1 - 10
of 173
pro vyhledávání: '"C. Chandra Sekhar"'
Publikováno v:
In Computer Vision and Image Understanding August 2022 221
Computer system models provide detailed answer to system performance.In this paper a two stage tandem network system with Blocking and Feedback is considered and it performance has been analyzed by spectral expansion method.The study state system wit
Externí odkaz:
http://arxiv.org/abs/1006.2693
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Munusamy, Hemalatha, C, Chandra Sekhar
Publikováno v:
Applied Intelligence; Oct2023, Vol. 53 Issue 20, p23349-23368, 20p
Publikováno v:
AAAI
Distance Metric Learning (DML) involves learning an embedding that brings similar examples closer while moving away dissimilar ones. Existing DML approaches make use of class labels to generate constraints for metric learning. In this paper, we addre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2289ab95374ce22511860ccd27709d78
https://doi.org/10.1609/aaai.v34i04.5795
https://doi.org/10.1609/aaai.v34i04.5795
Metric learning is an important problem in machine learning. It aims to group similar examples together. Existing state-of-the-art metric learning approaches require class labels to learn a metric. As obtaining class labels in all applications is not
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::94eb9abc030d820ffd1ef0ceeb2b29a7
http://arxiv.org/abs/2008.09880
http://arxiv.org/abs/2008.09880
Autor:
M. Hemalatha, C. Chandra Sekhar
Publikováno v:
WACV
In video captioning, the description of a video usually relies on the domain to which the video belongs. Typically, the videos belong to wide range domains such as sports, music, news, cooking, etc. In many cases, a video can be associated with more
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3ac5128a6ca0d2d08e6afab7065520a4
https://doi.org/10.1109/wacv45572.2020.9093344
https://doi.org/10.1109/wacv45572.2020.9093344
Speaker diarization is an important problem that is topical, and is especially useful as a preprocessor for conversational speech related applications. The objective of this paper is two-fold: (i) segment initialization by uniformly distributing spea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::73df228c7bf2117b16a61c45a44dce34
Autor:
Rupam Ojha, C. Chandra Sekhar
Publikováno v:
IJCNN
Acoustic modeling in large vocabulary continuous speech recognition systems is commonly done by building the models for subword units such as phonemes, syllables or senones. In recent years, various end-to-end systems using acoustic models built at g
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f7def3f5521ba0e93532312b37b1433d
https://doi.org/10.1109/ijcnn.2019.8851682
https://doi.org/10.1109/ijcnn.2019.8851682
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.