Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Renu Rameshan"'
Autor:
Renu Rameshan, Mohana Singh
Publikováno v:
PCS
Light field technology has increasingly attracted the attention of the research community with its many possible applications. The lenslet array in commercial plenoptic cameras helps capture both the spatial and angular information of light rays in a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7d17138db20b86a46892a9d1de531db7
https://doi.org/10.1109/pcs50896.2021.9477448
https://doi.org/10.1109/pcs50896.2021.9477448
Publikováno v:
ICPRAM
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cbcb15262eea49706d099324e75a8e2b
https://doi.org/10.5220/0010234805150522
https://doi.org/10.5220/0010234805150522
Autor:
Krishan Sharma, Renu Rameshan
Publikováno v:
IEEE transactions on neural networks and learning systems. 32(3)
Modeling image sets or videos as linear subspaces is quite popular for classification problems in machine learning. However, affine subspace modeling has not been explored much. In this article, we address the image sets classification problem by mod
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::51bcfb6daa36abcf046b12784612f22a
https://pubmed.ncbi.nlm.nih.gov/32275625
https://pubmed.ncbi.nlm.nih.gov/32275625
Publikováno v:
ICPRAM
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3f53690b78c11e17c3ecc925d840465e
https://doi.org/10.5220/0008924703080320
https://doi.org/10.5220/0008924703080320
Publikováno v:
ICPRAM
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e519663b1e3b3a21365ba69a436cecdd
https://doi.org/10.5220/0008940403210332
https://doi.org/10.5220/0008940403210332
Autor:
Krishan Sharma, Renu Rameshan
Publikováno v:
ICASSP
A video tensor is an organized multidimensional array of numerical values. In this paper, we explore the underlying manifold geometry of a video tensor by factorizing it using modified higher order singular value decomposition (HOSVD). Each factor (m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2e461704fbdfa6bcb7377a861eff77cb
https://doi.org/10.1109/icassp.2019.8682898
https://doi.org/10.1109/icassp.2019.8682898
TRINet: Tracking and Re-identification Network for Multiple Targets in Egocentric Videos Using LSTMs
Autor:
Renu Rameshan, Jyoti Nigam
Publikováno v:
Computer Analysis of Images and Patterns ISBN: 9783030298906
CAIP (2)
CAIP (2)
We present a recurrent network based novel framework for tracking and re-identifying multiple targets in first-person perspective. Even though LSTMs can act as a sequence classifier, most of the previous works in multi target tracking use their outpu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6898fcd5e059787f2d6d412045f7eb10
https://doi.org/10.1007/978-3-030-29891-3_38
https://doi.org/10.1007/978-3-030-29891-3_38
Publikováno v:
ICPRAM
AlexNet, one of the earliest and successful deep learning networks, has given great performance in image classification task. There are some fundamental properties for good classification such as: the network preserves the important information of th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e80082811175eb84936d20d739a001ef
https://doi.org/10.5220/0007582408600865
https://doi.org/10.5220/0007582408600865
Autor:
Krishan Sharma, Renu Rameshan
Publikováno v:
Journal of Visual Communication and Image Representation. 75:103045
In this paper, we explore the inherent geometry of video tensors by modeling them as points in product of Riemannian matrix manifolds. A video tensor is decomposed into three modes (factors) using matrix unfolding operation and each mode is represent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::863b6c7e8c7b5855ac7ff67c2065518d
https://doi.org/10.1016/j.jvcir.2021.103045
https://doi.org/10.1016/j.jvcir.2021.103045