[go: up one dir, main page]

Follow
Sameera Ramasinghe
Sameera Ramasinghe
Founding scientist, Pluralis Research
Verified email at pluralis.ai
Title
Cited by
Cited by
Year
Beyond periodicity: Towards a unifying framework for activations in coordinate-mlps
S Ramasinghe, S Lucey
European Conference on Computer Vision, 142-158, 2022
1772022
Gaussian activated neural radiance fields for high fidelity reconstruction and pose estimation
SF Chng, S Ramasinghe, J Sherrah, S Lucey
European Conference on Computer Vision, 264-280, 2022
1562022
Synthesized feature based few-shot class-incremental learning on a mixture of subspaces
A Cheraghian, S Rahman, S Ramasinghe, P Fang, C Simon, L Petersson, ...
Proceedings of the IEEE/CVF international conference on computer vision …, 2021
1062021
Rethinking positional encoding
J Zheng, S Ramasinghe, S Lucey
arXiv preprint arXiv:2107.02561, 2021
812021
Spectral-gans for high-resolution 3d point-cloud generation
S Ramasinghe, S Khan, N Barnes, S Gould
2020 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2020
462020
Enabling equivariance for arbitrary lie groups
LE MacDonald, S Ramasinghe, S Lucey
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2022
392022
Few-shot class-incremental learning for 3d point cloud objects
T Chowdhury, A Cheraghian, S Ramasinghe, S Ahmadi, M Saberi, ...
European Conference on Computer Vision, 204-220, 2022
312022
Accept the modality gap: An exploration in the hyperbolic space
S Ramasinghe, V Shevchenko, G Avraham, A Thalaiyasingam
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024
272024
Trading positional complexity vs deepness in coordinate networks
J Zheng, S Ramasinghe, X Li, S Lucey
European Conference on Computer Vision, 144-160, 2022
262022
Recognition of badminton strokes using dense trajectories
S Ramasinghe, KGM Chathuramali, R Rodrigo
7th International Conference on Information and Automation for …, 2014
262014
Action recognition by single stream convolutional neural networks: An approach using combined motion and static information
S Ramasinghe, R Rodrigo
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), 101-105, 2015
212015
On the frequency-bias of coordinate-mlps
S Ramasinghe, LE MacDonald, S Lucey
Advances in Neural Information Processing Systems 35, 796-809, 2022
202022
A sampling theory perspective on activations for implicit neural representations
H Saratchandran, S Ramasinghe, V Shevchenko, A Long, S Lucey
arXiv preprint arXiv:2402.05427, 2024
182024
A context-aware capsule network for multi-label classification
S Ramasinghe, CD Athuraliya, SH Khan
Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 0-0, 2018
182018
Combined static and motion features for deep-networks-based activity recognition in videos
S Ramasinghe, J Rajasegaran, V Jayasundara, K Ranasinghe, ...
IEEE Transactions on Circuits and Systems for Video Technology 29 (9), 2693-2707, 2017
172017
Backpropagation-free network for 3d test-time adaptation
Y Wang, A Cheraghian, Z Hayder, J Hong, S Ramasinghe, S Rahman, ...
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024
162024
Robust normalizing flows using Bernstein-type polynomials
S Ramasinghe, K Fernando, S Khan, N Barnes
arXiv preprint arXiv:2102.03509, 2021
152021
How much does initialization affect generalization?
S Ramasinghe, LE MacDonald, M Farazi, H Saratchandran, S Lucey
International Conference on Machine Learning, 28637-28655, 2023
132023
Learning positional embeddings for coordinate-mlps
S Ramasinghe, S Lucey
arXiv preprint arXiv:2112.11577, 2021
122021
Representation learning on unit ball with 3d roto-translational equivariance
S Ramasinghe, S Khan, N Barnes, S Gould
International Journal of Computer Vision 128 (6), 1612-1634, 2020
122020
The system can't perform the operation now. Try again later.
Articles 1–20