Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Sameera Ramasinghe"'
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198267
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ac4e40b0ad785140a78d5337f0210309
https://doi.org/10.1007/978-3-031-19827-4_16
https://doi.org/10.1007/978-3-031-19827-4_16
Autor:
Townim Chowdhury, Ali Cheraghian, Sameera Ramasinghe, Sahar Ahmadi, Morteza Saberi, Shafin Rahman
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200434
Few-shot class-incremental learning (FSCIL) aims to incrementally fine-tune a model (trained on base classes) for a novel set of classes using a few examples without forgetting the previous training. Recent efforts address this problem primarily on 2
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bee9aed4bc70efb7ec4a6b89d75dad78
https://doi.org/10.1007/978-3-031-20044-1_12
https://doi.org/10.1007/978-3-031-20044-1_12
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198113
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6c0d55e3309b661064c519736d0cb8bd
https://doi.org/10.1007/978-3-031-19812-0_9
https://doi.org/10.1007/978-3-031-19812-0_9
Autor:
Sameera Ramasinghe, Simon Lucey
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198267
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a8ab1cea055edf7d5028c7a199c880f1
https://doi.org/10.1007/978-3-031-19827-4_9
https://doi.org/10.1007/978-3-031-19827-4_9
Autor:
Ali Cheraghian, Shafin Rahman, Sameera Ramasinghe, Pengfei Fang, Christian Simon, Lars Petersson, Mehrtash Harandi
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::137c67b88b2083ba0d4c0bc9af917e1e
https://doi.org/10.1109/iccv48922.2021.00854
https://doi.org/10.1109/iccv48922.2021.00854
Autor:
Jathushan Rajasegaran, Sameera Ramasinghe, Vinoj Jayasundara, Ranga Rodrigo, Kanchana Ranasinghe, Ajith Pasqual
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 29:2693-2707
Activity recognition in videos in a deep-learning setting—or otherwise—uses both static and pre-computed motion components. The method of combining the two components, while keeping the burden on the deep network less, still remains uninvestigate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::08c5fc3c34108ff2260e69c535f64b0a
https://doi.org/10.1109/tcsvt.2017.2760858
https://doi.org/10.1109/tcsvt.2017.2760858
Publikováno v:
IROS
Point-clouds are a popular choice for vision and graphics tasks due to their accurate shape description and direct acquisition from range-scanners. This demands the ability to synthesize and reconstruct high-quality point-clouds. Current deep generat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::59169b8960e920ec8fcce5a2ad683fe5
https://doi.org/10.1109/iros45743.2020.9341265
https://doi.org/10.1109/iros45743.2020.9341265
Convolution is an integral operation that defines how the shape of one function is modified by another function. This powerful concept forms the basis of hierarchical feature learning in deep neural networks. Although performing convolution in Euclid
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2419bd9a568302ff14cbda8786d9448f
http://arxiv.org/abs/1912.01454
http://arxiv.org/abs/1912.01454
Publikováno v:
WACV
Existing networks directly learn feature representations on 3D point clouds for shape analysis. We argue that 3D point clouds are highly redundant and hold irregular (permutation-invariant) structure, which makes it difficult to achieve inter-class d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fac00243e00fbb84037af8a57c7ccebd
http://arxiv.org/abs/1908.10209
http://arxiv.org/abs/1908.10209
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030110147
ECCV Workshops (3)
ECCV Workshops (3)
Recently proposed Capsule Network is a brain inspired architecture that brings a new paradigm to deep learning by modelling input domain variations through vector based representations. Despite being a seminal contribution, CapsNet does not explicitl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f05865202d2274c2020f581a94a9d776
https://doi.org/10.1007/978-3-030-11015-4_40
https://doi.org/10.1007/978-3-030-11015-4_40