Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Suranjana Samanta"'
Autor:
Suranjana Samanta, Sukhendu Das
Publikováno v:
IET Computer Vision, Vol 10, Iss 5, Pp 443-449 (2016)
Domain adaptation is used for machine learning tasks, when the distribution of the training (obtained from source domain) set differs from that of the testing (referred as target domain) set. In the work presented in this study, the problem of unsupe
Externí odkaz:
https://doaj.org/article/ed59119e6bdc4709a69e1c207ded949d
Publikováno v:
2022 IEEE 15th International Conference on Cloud Computing (CLOUD).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fcc1b81a5fcf0d2eca28b7fffae31335
https://doi.org/10.1109/cloud55607.2022.00040
https://doi.org/10.1109/cloud55607.2022.00040
Publikováno v:
Advances in Knowledge Discovery and Data Mining ISBN: 9783030757670
PAKDD (3)
PAKDD (3)
Transformer-based models, such as GPT-2, have revolutionized the landscape of dialogue generation by capturing the long-range structures through language modeling. Though these models have exhibited excellent language coherence, they often lack relev
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1d4351ceb7ca8fcd03056a42dd2ffa1e
https://doi.org/10.1007/978-3-030-75768-7_23
https://doi.org/10.1007/978-3-030-75768-7_23
Autor:
Stefan Siegel, Matthias J. Schmand, Joseph A. O'Sullivan, Robert A. Mintzer, Maurizio Conti, Ke Li, Yuan-Chuan Tai, Suranjana Samanta, Jianyong Jiang, Sanghee Cho
Publikováno v:
IEEE Trans Med Imaging
A novel technique, called augmented whole-body scanning via magnifying PET (AWSM-PET), that improves the sensitivity and lesion detectability of a PET scanner for whole-body imaging is proposed and evaluated. A Siemens Biograph Vision PET/CT scanner
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5594dd411d47ad9a3ab35050ff16c55f
https://europepmc.org/articles/PMC7673659/
https://europepmc.org/articles/PMC7673659/
The sudden widespread menace created by the present global pandemic COVID-19 has had an unprecedented effect on our lives. Man-kind is going through humongous fear and dependence on social media like never before. Fear inevitably leads to panic, spec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::22b7e4d4f38e8e436a77f620623842f8
http://arxiv.org/abs/2010.06906
http://arxiv.org/abs/2010.06906
Autor:
Alan Z. Register, Martin P. Tornai, Segei Dolinsky, Joseph A. O'Sullivan, Mark B. Williams, Stanislaw Majewski, Suranjana Samanta, Timothy G. Turkington, Yuan-Chuan Tai, Jianyong Jiang
Publikováno v:
15th International Workshop on Breast Imaging (IWBI2020).
This paper presents a new high-sensitivity PET geometry for high fidelity MRI-compatible PET breast imaging which can scan both breasts simultaneously and have: high sensitivity and resolution; compatibility with MR-breast imaged volume; complete vis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7bad9b6f0144f340d0667d4aae7e26be
https://doi.org/10.1117/12.2563650
https://doi.org/10.1117/12.2563650
Autor:
Soumava Paul, Saneem A. Chemmengath, Karthik Sankaranarayanan, Suranjana Samanta, Samarth Bharadwaj
Zero-shot learning (ZSL) algorithms typically work by exploiting attribute correlations to be able to make predictions in unseen classes. However, these correlations do not remain intact at test time in most practical settings and the resulting chang
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4de6b4682794984a33f3008b946d6b67
http://arxiv.org/abs/2003.00845
http://arxiv.org/abs/2003.00845
Publikováno v:
ICPR
Recently, deep learning frameworks have been shown to learn a feature embedding that captures fine-grained image similarity using image triplets or quadruplets that consider pairwise relationships between image pairs. In real-world datasets, a class
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ac24ab496f47bb7a8b6cb131703dbcae
https://doi.org/10.1109/icpr.2018.8545492
https://doi.org/10.1109/icpr.2018.8545492
Autor:
Suranjana Samanta, Sameep Mehta
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319769400
ECIR
ECIR
Adversarial samples are strategically modified samples, which are crafted with the purpose of fooling a trained classifier. In this paper, we propose a new method of crafting adversarial text samples by modification of the original samples. Modificat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::243d24a6e30c148dfe2f93108f139d4d
https://doi.org/10.1007/978-3-319-76941-7_71
https://doi.org/10.1007/978-3-319-76941-7_71
Autor:
Sukhendu Das, Suranjana Samanta
Publikováno v:
IET Image Processing. 9:925-930
This study describes a new technique of unsupervised domain adaptation based on eigenanalysis in kernel space, for the purpose of categorisation tasks. The authors propose a transformation of data in source domain, such that the eigenvectors and eige
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9cf9c7a8f34eedd9e6d833df59b74de1
https://doi.org/10.1049/iet-ipr.2014.0754
https://doi.org/10.1049/iet-ipr.2014.0754