Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Titir Dutta"'
Publikováno v:
Pattern Recognition Letters. 147:93-99
The significant amount of training data required for training Convolutional Neural Networks has become a bottleneck for applications like semantic segmentation. Few-shot semantic segmentation algorithms address this problem, with an aim to achieve go
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fdc6f3e153533ca13054d7d148404951
https://doi.org/10.1016/j.patrec.2021.03.036
https://doi.org/10.1016/j.patrec.2021.03.036
Publikováno v:
IEEE Transactions on Multimedia. 23:2833-2842
The goal of zero-shot sketch-based image retrieval is to retrieve relevant images from a search set against a hand-drawn sketch query, which belongs to a class, previously unseen by the model. The knowledge gap between such unseen and seen classes al
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c405e6bb456a168ba66fc6cf4eabe3fb
https://doi.org/10.1109/tmm.2020.3017918
https://doi.org/10.1109/tmm.2020.3017918
Publikováno v:
Proceedings of the Twelfth Indian Conference on Computer Vision, Graphics and Image Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a75e0f7eeb650509ed814dde744fdfab
https://doi.org/10.1145/3490035.3490303
https://doi.org/10.1145/3490035.3490303
Autor:
Titir Dutta, Soma Biswas
Publikováno v:
IEEE Transactions on Image Processing. 28:5953-5962
Cross-modal retrieval is an important research area due to its wide range of applications, and several algorithms have been proposed to address this task. We feel that it is the right time to take a step hack and analyze the current status of researc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fdab1ae82fa0c36546094b03d78eeeed
https://doi.org/10.1109/tip.2019.2923287
https://doi.org/10.1109/tip.2019.2923287
Autor:
Megh Bhalerao, Anurag Singh, Balasubramanian Vengatesan, Sawa Takamuku, Aditya Chepuri, Soma Biswas, Naren Doraiswamy, Naotake Natori, Titir Dutta
Publikováno v:
CVPR Workshops
Recently, semi-supervised domain adaptation (SSDA) approaches have shown impressive performance for the domain adaptation task. They effectively utilize few labeled target samples along with the unlabeled data to account for the distribution shift ac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0cdb5c59ae2a9a3aef845b3f8fca5e3e
https://doi.org/10.1109/cvprw53098.2021.00305
https://doi.org/10.1109/cvprw53098.2021.00305
Nanoporous organic polymers with distinct morphologies are of immense interest for a broad spectrum of applications ranging from catalysis to molecular separation, energy storage, and energy conversion. However, developing facile and versatile method
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::41ab0f813511ac2c307ec1d57fcd3cb6
https://doi.org/10.26434/chemrxiv.14333936.v1
https://doi.org/10.26434/chemrxiv.14333936.v1
Autor:
Titir Dutta, Soma Biswas
Publikováno v:
WACV
Sketch-based image retrieval (SBIR) is gaining increasing popularity because of its flexibility to search natural images using unrestricted hand-drawn sketch query. Here, we address a related, but relatively unexplored problem, where the users can al
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6b9bf3ab77b9cd4c23458322f0491c1f
https://doi.org/10.1109/wacv45572.2020.9093289
https://doi.org/10.1109/wacv45572.2020.9093289
Publikováno v:
WACV
Generative models have achieved impressive performance for the generalized zero-shot learning task by learning the mapping from attributes to feature space. In this work, we propose to derive semantic inferences from images and use them for the gener
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::118d09e3cfc53e40e898afc953da3583
https://doi.org/10.1109/wacv45572.2020.9093625
https://doi.org/10.1109/wacv45572.2020.9093625
Publikováno v:
Circuits, Systems, and Signal Processing. 37:847-861
Orthogonal frequency-division multiplexing (OFDM) is a multi-carrier modulation scheme that has been employed in many communication standards. The performance of OFDM is severely degraded by the presence of impulsive noise caused due to different non
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6c2d5c153c62bbc790b3b104c507461f
https://doi.org/10.1007/s00034-017-0573-y
https://doi.org/10.1007/s00034-017-0573-y
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585570
ECCV (5)
ECCV (5)
Data from new categories are continuously being discovered, which has sparked significant amount of research in developing approaches which generalize to previously unseen categories, i.e. zero-shot setting. Zero-shot sketch-based image retrieval (ZS
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::00a5dafd417a340508685d3c2fffe52c
https://doi.org/10.1007/978-3-030-58558-7_21
https://doi.org/10.1007/978-3-030-58558-7_21