| Neural networks for topology optimization I Sosnovik, I Oseledets Russian Journal of Numerical Analysis and Mathematical Modelling 34 (4), 215-223, 2019 | 338 | 2019 |
| Scale-equivariant steerable networks I Sosnovik, M Szmaja, A Smeulders arXiv preprint arXiv:1910.11093, 2019 | 176 | 2019 |
| Scale equivariance improves siamese tracking I Sosnovik, A Moskalev, AWM Smeulders Proceedings of the IEEE/CVF winter conference on applications of computer …, 2021 | 110 | 2021 |
| Semi-conditional normalizing flows for semi-supervised learning A Atanov, A Volokhova, A Ashukha, I Sosnovik, D Vetrov arXiv preprint arXiv:1905.00505, 2019 | 37 | 2019 |
| Disco: accurate discrete scale convolutions I Sosnovik, A Moskalev, A Smeulders arXiv preprint arXiv:2106.02733, 2021 | 36 | 2021 |
| Liegg: Studying learned lie group generators A Moskalev, A Sepliarskaia, I Sosnovik, A Smeulders Advances in Neural Information Processing Systems 35, 25212-25223, 2022 | 29 | 2022 |
| How to transform kernels for scale-convolutions I Sosnovik, A Moskalev, A Smeulders Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 13 | 2021 |
| Contrasting quadratic assignments for set-based representation learning A Moskalev, I Sosnovik, V Fischer, A Smeulders European Conference on Computer Vision, 88-104, 2022 | 9 | 2022 |
| PIE: Pseudo-Invertible Encoder JJ Beitler, I Sosnovik, A Smeulders arXiv preprint arXiv:2111.00619, 2021 | 8* | 2021 |
| Recognition of objects in images with equivariance or invariance in relation to the object size A Moskalev, I Sosnovik, A Smeulders, K Groh US Patent 11,886,995, 2024 | 2 | 2024 |
| Learning to Summarize Videos by Contrasting Clips I Sosnovik, A Moskalev, C Kaandorp, A Smeulders arXiv preprint arXiv:2301.05213, 2023 | 2 | 2023 |
| Method and apparatus for processing sensor data using a convolutional neural network A Smeulders, I Sosnovik, K Groh, M Szmaja US Patent App. 17/022,895, 2021 | 2 | 2021 |
| Symmetry-based learning from limited data I Sosnovik Ivan Sosnovik, 2023 | 1 | 2023 |
| Built-in Elastic Transformations for Improved Robustness S Gulshad, I Sosnovik, A Smeulders arXiv preprint arXiv:2107.09391, 2021 | 1 | 2021 |
| Training a machine learnable model to estimate relative object scale I Sosnovik, A Smeulders, K Groh US Patent 12,125,228, 2024 | | 2024 |
| Device and method for training a scale-equivariant convolutional neural network I Sosnovik, A Smeulders, K Groh US Patent App. 17/446,668, 2022 | | 2022 |
| Wiggling Weights to Improve the Robustness of Classifiers S Gulshad, I Sosnovik, A Smeulders arXiv preprint arXiv:2111.09779, 2021 | | 2021 |
| Two is a crowd: tracking relations in videos A Moskalev, I Sosnovik, A Smeulders arXiv preprint arXiv:2108.05331, 2021 | | 2021 |
| Relational Prior for Multi-Object Tracking A Moskalev, I Sosnovik, A Smeulders Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | | 2021 |
| Scale Equivariance Improves Siamese Tracking Supplementary Material I Sosnovik, A Moskalev, A Smeulders | | |
Arnold SmeuldersProfessor of Computer Science, University of AmsterdamPatvirtintas el. paštas uva.nl