Sameera Ramasinghe

77 papers A* 18A 4B 1C 1Misc 1Journal 42Unranked 10

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	AsyncMesh: Fully Asynchronous Optimization for Data and Pipeline Parallelism. CoRR Thalaiyasingam Ajanthan, Sameera Ramasinghe, Gil Avraham, Hadi Mohaghegh Dolatabadi, Chamin Hewa Koneputugodage, Violetta Shevchenko, Yan Zuo, Alexander Long
2026	J	`jnl`	NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training. CoRR Hadi Mohaghegh Dolatabadi, Thalaiyasingam Ajanthan, Sameera Ramasinghe, Chamin Hewa Koneputugodage, Shamane Siriwardhana, Violetta Shevchenko, Karol Pajak, James Snewin, Gil Avraham, Alexander Long
2026	J	`jnl`	SENTINEL: Stagewise Integrity Verification for Pipeline Parallel Decentralized Training. CoRR Hadi Mohaghegh Dolatabadi, Thalaiyasingam Ajanthan, Sameera Ramasinghe, Chamin Hewa Koneputugodage, Gil Avraham, Yan Zuo, Violetta Shevchenko, Alexander Long
2025	J	`jnl`	DARB-Splatting: Generalizing Splatting with Decaying Anisotropic Radial Basis Functions. CoRR Vishagar Arunan, Saeedha Nazar, Hashiru Pramuditha, Vinasirajan Viruthshaan, Sameera Ramasinghe, Simon Lucey, Ranga Rodrigo
2025	J	`jnl`	LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit Calibration. Trans. Mach. Learn. Res. Md. Ismail Hossain, Mirza M. Lutfe Elahi, Sameera Ramasinghe, Ali Cheraghian, Fuad Rahman, Nabeel Mohammed, Shafin Rahman
2025	A*	`conf`	Nesterov Method for Asynchronous Pipeline Parallel Optimization. ICML Thalaiyasingam Ajanthan, Sameera Ramasinghe, Yan Zuo, Gil Avraham, Alexander Long
2025	J	`jnl`	Nesterov Method for Asynchronous Pipeline Parallel Optimization. CoRR Thalaiyasingam Ajanthan, Sameera Ramasinghe, Yan Zuo, Gil Avraham, Alexander Long
2025	J	`jnl`	Protocol Models: Scaling Decentralized Training with Communication-Efficient Model Parallelism. CoRR Sameera Ramasinghe, Thalaiyasingam Ajanthan, Gil Avraham, Yan Zuo, Alexander Long
2025	—	`conf`	QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-free Document Understanding. CVPR Workshops Binh M. Le, Shaoyuan Xu, Jinmiao Fu, Zhishen Huang, Moyan Li, Yanhui Guo, Hongdong Li, Sameera Ramasinghe, Bryan Wang
2025	J	`jnl`	QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-free Visual Document Understanding. CoRR Binh M. Le, Shaoyuan Xu, Jinmiao Fu, Zhishen Huang, Moyan Li, Yanhui Guo, Hongdong Li, Sameera Ramasinghe, Bryan Wang
2025	B	`conf`	Scaling Prompt Instructed Zero Shot Composed Image Retrieval with Image-Only Data. IJCNN Yiqun Duan, Sameera Ramasinghe, Stephen Gould, Thalaiyasingam Ajanthan
2025	J	`jnl`	Scaling Prompt Instructed Zero Shot Composed Image Retrieval with Image-Only Data. CoRR Yiqun Duan, Sameera Ramasinghe, Stephen Gould, Thalaiyasingam Ajanthan
2025	A	`conf`	Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models. WACV Hamidreza Dastmalchi, Aijun An, Ali Cheraghian, Shafin Rahman, Sameera Ramasinghe
2025	J	`jnl`	VI3NR: Variance Informed Initialization for Implicit Neural Representations. CoRR Chamin Hewa Koneputugodage, Yizhak Ben-Shabat, Sameera Ramasinghe, Stephen Gould
2025	A*	`conf`	VI^3NR: Variance Informed Initialization for Implicit Neural Representations. CVPR Chamin Hewa Koneputugodage, Yizhak Ben-Shabat, Sameera Ramasinghe, Stephen Gould
2024	J	`jnl`	A Sampling Theory Perspective on Activations for Implicit Neural Representations. CoRR Hemanth Saratchandran, Sameera Ramasinghe, Violetta Shevchenko, Alexander Long, Simon Lucey
2024	A*	`conf`	A sampling theory perspective on activations for implicit neural representations. ICML Hemanth Saratchandran, Sameera Ramasinghe, Violetta Shevchenko, Alexander Long, Simon Lucey
2024	A*	`conf`	Accept the Modality Gap: An Exploration in the Hyperbolic Space. CVPR Sameera Ramasinghe, Violetta Shevchenko, Gil Avraham, Thalaiyasingam Ajanthan
2024	A*	`conf`	BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling. AAAI Sameera Ramasinghe, Violetta Shevchenko, Gil Avraham, Anton van den Hengel
2024	A*	`conf`	Backpropagation-free Network for 3D Test-time Adaptation. CVPR Yanshuo Wang, Ali Cheraghian, Zeeshan Hayder, Jie Hong, Sameera Ramasinghe, Shafin Rahman, David Ahmedt-Aristizabal, Xuesong Li, Lars Petersson, Mehrtash Harandi
2024	J	`jnl`	Backpropagation-free Network for 3D Test-time Adaptation. CoRR Yanshuo Wang, Ali Cheraghian, Zeeshan Hayder, Jie Hong, Sameera Ramasinghe, Shafin Rahman, David Ahmedt-Aristizabal, Xuesong Li, Lars Petersson, Mehrtash Harandi
2024	—	`conf`	Canonical Shape Projection Is All You Need for 3D Few-Shot Class Incremental Learning. ECCV (41) Ali Cheraghian, Zeeshan Hayder, Sameera Ramasinghe, Shafin Rahman, Javad Jafaryahya, Lars Petersson, Mehrtash Harandi
2024	A*	`conf`	From Activation to Initialization: Scaling Insights for Optimizing Neural Fields. CVPR Hemanth Saratchandran, Sameera Ramasinghe, Simon Lucey
2024	J	`jnl`	From Activation to Initialization: Scaling Insights for Optimizing Neural Fields. CoRR Hemanth Saratchandran, Sameera Ramasinghe, Simon Lucey
2024	A*	`conf`	Improving the Convergence of Dynamic NeRFs via Optimal Transport. ICLR Sameera Ramasinghe, Violetta Shevchenko, Gil Avraham, Hisham Husain, Anton van den Hengel
2024	J	`jnl`	Learning Visual Hierarchies with Hyperbolic Embeddings. CoRR Ziwei Wang, Sameera Ramasinghe, Chenchen Xu, Julien Monteil, Loris Bazzani, Thalaiyasingam Ajanthan
2024	A*	`conf`	Neural Experts: Mixture of Experts for Implicit Neural Representations. NeurIPS Yizhak Ben-Shabat, Chamin Hewa Koneputugodage, Sameera Ramasinghe, Stephen Gould
2024	J	`jnl`	Neural Experts: Mixture of Experts for Implicit Neural Representations. CoRR Yizhak Ben-Shabat, Chamin Hewa Koneputugodage, Sameera Ramasinghe, Stephen Gould
2024	—	`conf`	Robust Point Cloud Processing Through Positional Embedding. 3DV Jianqiao Zheng, Xueqian Li, Sameera Ramasinghe, Simon Lucey
2024	J	`jnl`	Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models. CoRR Hamidreza Dastmalchi, Aijun An, Ali Cheraghian, Shafin Rahman, Sameera Ramasinghe
2024	A*	`conf`	ViewFusion: Towards Multi-View Consistency via Interpolated Denoising. CVPR Xianghui Yang, Yan Zuo, Sameera Ramasinghe, Loris Bazzani, Gil Avraham, Anton van den Hengel
2024	J	`jnl`	ViewFusion: Towards Multi-View Consistency via Interpolated Denoising. CoRR Xianghui Yang, Yan Zuo, Sameera Ramasinghe, Loris Bazzani, Gil Avraham, Anton van den Hengel
2023	A*	`conf`	A Learnable Radial Basis Positional Embedding for Coordinate-MLPs. AAAI Sameera Ramasinghe, Simon Lucey
2023	J	`jnl`	BaLi-RF: Bandlimited Radiance Fields for Dynamic Scene Modeling. CoRR Sameera Ramasinghe, Violetta Shevchenko, Gil Avraham, Anton van den Hengel
2023	A*	`conf`	Curvature-Aware Training for Coordinate Networks. ICCV Hemanth Saratchandran, Shin-Fang Ch'ng, Sameera Ramasinghe, Lachlan E. MacDonald, Simon Lucey
2023	J	`jnl`	Curvature-Aware Training for Coordinate Networks. CoRR Hemanth Saratchandran, Shin-Fang Ch'ng, Sameera Ramasinghe, Lachlan E. MacDonald, Simon Lucey
2023	A*	`conf`	How much does Initialization Affect Generalization? ICML Sameera Ramasinghe, Lachlan Ewen MacDonald, Moshiur R. Farazi, Hemanth Saratchandran, Simon Lucey
2023	J	`jnl`	LumiNet: The Bright Side of Perceptual Knowledge Distillation. CoRR Md. Ismail Hossain, Mirza M. Lutfe Elahi, Sameera Ramasinghe, Ali Cheraghian, Fuad Rahman, Nabeel Mohammed, Shafin Rahman
2023	J	`jnl`	On the effectiveness of neural priors in modeling dynamical systems. CoRR Sameera Ramasinghe, Hemanth Saratchandran, Violetta Shevchenko, Simon Lucey
2023	J	`jnl`	Robust Point Cloud Processing through Positional Embedding. CoRR Jianqiao Zheng, Xueqian Li, Sameera Ramasinghe, Simon Lucey
2022	—	`conf`	Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPs. ECCV (33) Sameera Ramasinghe, Simon Lucey
2022	A*	`conf`	Enabling Equivariance for Arbitrary Lie Groups. CVPR Lachlan E. MacDonald, Sameera Ramasinghe, Simon Lucey
2022	—	`conf`	Few-Shot Class-Incremental Learning for 3D Point Cloud Objects. ECCV (20) Townim F. Chowdhury, Ali Cheraghian, Sameera Ramasinghe, Sahar Ahmadi, Morteza Saberi, Shafin Rahman
2022	J	`jnl`	Few-shot Class-incremental Learning for 3D Point Cloud Objects. CoRR Townim F. Chowdhury, Ali Cheraghian, Sameera Ramasinghe, Sahar Ahmadi, Morteza Saberi, Shafin Rahman
2022	J	`jnl`	GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimation. CoRR Shin-Fang Ch'ng, Sameera Ramasinghe, Jamie Sherrah, Simon Lucey
2022	—	`conf`	Gaussian Activated Neural Radiance Fields for High Fidelity Reconstruction and Pose Estimation. ECCV (33) Shin-Fang Ch'ng, Sameera Ramasinghe, Jamie Sherrah, Simon Lucey
2022	J	`jnl`	How You Start Matters for Generalization. CoRR Sameera Ramasinghe, Lachlan E. MacDonald, Moshiur R. Farazi, Hemanth Saratchandran, Simon Lucey
2022	J	`jnl`	On Regularizing Coordinate-MLPs. CoRR Sameera Ramasinghe, Lachlan E. MacDonald, Simon Lucey
2022	A*	`conf`	On the Frequency-bias of Coordinate-MLPs. NeurIPS Sameera Ramasinghe, Lachlan E. MacDonald, Simon Lucey
2022	A	`conf`	Robust normalizing flows using Bernstein-type polynomials. BMVC Sameera Ramasinghe, Kasun Fernando, Salman Khan, Nick Barnes
2022	—	`conf`	Trading Positional Complexity vs Deepness in Coordinate Networks. ECCV (27) Jianqiao Zheng, Sameera Ramasinghe, Xueqian Li, Simon Lucey
2022	J	`jnl`	Trading Positional Complexity vs. Deepness in Coordinate Networks. CoRR Jianqiao Zheng, Sameera Ramasinghe, Xueqian Li, Simon Lucey
2021	J	`jnl`	Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPs. CoRR Sameera Ramasinghe, Simon Lucey
2021	A*	`conf`	Conditional Generative Modeling via Learning the Latent Space. ICLR Sameera Ramasinghe, Kanchana Nisal Ranasinghe, Salman H. Khan, Nick Barnes, Stephen Gould
2021	J	`jnl`	Enabling equivariance for arbitrary Lie groups. CoRR Lachlan E. MacDonald, Sameera Ramasinghe, Simon Lucey
2021	J	`jnl`	Learning Positional Embeddings for Coordinate-MLPs. CoRR Sameera Ramasinghe, Simon Lucey
2021	J	`jnl`	Rethinking Positional Encoding. CoRR Jianqiao Zheng, Sameera Ramasinghe, Simon Lucey
2021	A*	`conf`	Rethinking conditional GAN training: An approach using geometrically structured latent manifolds. NeurIPS Sameera Ramasinghe, Moshiur R. Farazi, Salman H. Khan, Nick Barnes, Stephen Gould
2021	J	`jnl`	Robust normalizing flows using Bernstein-type polynomials. CoRR Sameera Ramasinghe, Kasun Fernando, Salman H. Khan, Nick Barnes
2021	A*	`conf`	Synthesized Feature based Few-Shot Class-Incremental Learning on a Mixture of Subspaces. ICCV Ali Cheraghian, Shafin Rahman, Sameera Ramasinghe, Pengfei Fang, Christian Simon, Lars Petersson, Mehrtash Harandi
2020	A	`conf`	Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes. WACV Sameera Ramasinghe, Salman H. Khan, Nick Barnes, Stephen Gould
2020	J	`jnl`	Conditional Generative Modeling via Learning the Latent Space. CoRR Sameera Ramasinghe, Kanchana Ranasinghe, Salman H. Khan, Nick Barnes, Stephen Gould
2020	J	`jnl`	How to train your conditional GAN: An approach using geometrically structured latent manifolds. CoRR Sameera Ramasinghe, Moshiur R. Farazi, Salman H. Khan, Nick Barnes, Stephen Gould
2020	C	`conf`	Learned and Hand-crafted Feature Fusion in Unit Ball for 3D Object Classification. ICPRAM Sameera Ramasinghe, Salman H. Khan, Nick Barnes
2020	J	`jnl`	Representation Learning on Unit Ball with 3D Roto-translational Equivariance. Int. J. Comput. Vis. Sameera Ramasinghe, Salman H. Khan, Nick Barnes, Stephen Gould
2020	A	`conf`	Spectral-GANs for High-Resolution 3D Point-cloud Generation. IROS Sameera Ramasinghe, Salman H. Khan, Nick Barnes, Stephen Gould
2019	J	`jnl`	Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes. CoRR Sameera Ramasinghe, Salman H. Khan, Nick Barnes, Stephen Gould
2019	J	`jnl`	Combined Static and Motion Features for Deep-Networks-Based Activity Recognition in Videos. IEEE Trans. Circuits Syst. Video Technol. Sameera Ramasinghe, Jathushan Rajasegaran, Vinoj Jayasundara, Kanchana Ranasinghe, Ranga Rodrigo, Ajith A. Pasqual
2019	J	`jnl`	Representation Learning on Unit Ball with 3D Roto-Translational Equivariance. CoRR Sameera Ramasinghe, Salman H. Khan, Nick Barnes, Stephen Gould
2019	J	`jnl`	Spectral-GANs for High-Resolution 3D Point-cloud Generation. CoRR Sameera Ramasinghe, Salman H. Khan, Nick Barnes, Stephen Gould
2019	J	`jnl`	Volumetric Convolution: Automatic Representation Learning in Unit Ball. CoRR Sameera Ramasinghe, Salman H. Khan, Nick Barnes
2018	—	`conf`	A Context-Aware Capsule Network for Multi-label Classification. ECCV Workshops (3) Sameera Ramasinghe, C. D. Athuraliya, Salman H. Khan
2018	J	`jnl`	A Context-aware Capsule Network for Multi-label Classification. CoRR Sameera Ramasinghe, C. D. Athuralya, Salman H. Khan
2018	J	`jnl`	Combined Static and Motion Features for Deep-Networks Based Activity Recognition in Videos. CoRR Sameera Ramasinghe, Jathushan Rajasegaran, Vinoj Jayasundara, Kanchana Ranasinghe, Ranga Rodrigo, Ajith A. Pasqual
2017	Misc	`conf`	Micro Actions and Deep Static Features for Activity Recognition. DICTA Sameera Ramasinghe, Jathushan Rajasegaran, Vinoj Jayasundara, Kanchana Ranasinghe, Ranga Rodrigo, Ajith A. Pasqual
2016	—	`conf`	Poster: Advanced Feature Based Deep Learning for Intelligent Human Activity Recognition: An Approach using Scene Context and Composition of Sub Events. MobiSys (Companion Volume) Sameera Ramasinghe
2015	—	`conf`	Action recognition by single stream convolutional neural networks: An approach using combined motion and static information. ACPR Sameera Ramasinghe, Ranga Rodrigo