| Sstvos: Sparse spatiotemporal transformers for video object segmentation B Duke, A Ahmed, C Wolf, P Aarabi, GW Taylor Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2021 | 185 | 2021 |
| Loho: Latent optimization of hairstyles via orthogonalization R Saha, B Duke, F Shkurti, GW Taylor, P Aarabi Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2021 | 52 | 2021 |
| Sparsifiner: Learning sparse instance-dependent attention for efficient vision transformers C Wei, B Duke, R Jiang, P Aarabi, GW Taylor, F Shkurti Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 13 | 2023 |
| Generalized hadamard-product fusion operators for visual question answering B Duke, GW Taylor 2018 15th Conference on Computer and Robot Vision (CRV), 39-46, 2018 | 13 | 2018 |
| Exploring gradient-based multi-directional controls in gans Z Chen, R Jiang, B Duke, H Zhao, P Aarabi European Conference on Computer Vision, 104-119, 2022 | 12 | 2022 |
| The gist and rist of iterative self-training for semi-supervised segmentation EW Teh, T DeVries, B Duke, R Jiang, P Aarabi, GW Taylor 2022 19th Conference on Robots and Vision (CRV), 58-66, 2022 | 9 | 2022 |
| Image processing using a convolutional neural network to track a plurality of objects B Duke, A Ahmed, E Phung, I Kezele, P Aarabi US Patent 11,410,314, 2022 | 8 | 2022 |
| Lightweight real-time makeup try-on in mobile browsers with tiny CNN models for facial tracking TX Li, Z Yu, E Phung, B Duke, I Kezele, P Aarabi arXiv preprint arXiv:1906.02260, 2019 | 6 | 2019 |
| Real‐time Virtual‐Try‐On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers R Kips, R Jiang, S Ba, B Duke, M Perrot, P Gori, I Bloch Computer Graphics Forum 41 (2), 29-40, 2022 | 4 | 2022 |
| Style try-on with reverse GANs R Saha, B Duke US Patent 12,002,136, 2024 | 3 | 2024 |
| Nail Polish Try-On: Realtime Semantic Segmentation of Small Objects for Native and Browser Smartphone AR Applications B Duke, A Ahmed, E Phung, I Kezele, P Aarabi arXiv preprint arXiv:1906.02222, 2019 | 2 | 2019 |
| Attention and Fusion of Deep Representations for Computer Vision B Duke University of Guelph, 2020 | 1 | 2020 |
| Method and system for object antialiasing in an augmented reality experience B Duke US Patent App. 18/086,754, 2024 | | 2024 |
| Method, apparatus and system for image-to-image translation R Jiang, B Duke, P Aarabi US Patent App. 17/994,792, 2024 | | 2024 |
| Methods and apparatus for determining and using controllable directions of gan space C Zikun, R Jiang, B Duke, P Aarabi US Patent App. 18/227,546, 2024 | | 2024 |
| End-to-end merge for video object segmentation (VOS) A Ahmed, I Kezele, P Aarabi, B Duke US Patent 11,748,888, 2023 | | 2023 |
| Faulty Neural Networks SW Chen, B Duke, P Aarabi 2023 IEEE Conference on Artificial Intelligence (CAI), 290-291, 2023 | | 2023 |
| Sparse Attention Mechanisms in Vision Transformers: from Spatiotemporal Transformers to Instance-Dependent Attention Patterns B Duke University of Toronto (Canada), 2023 | | 2023 |
| Synthesizing ultraviolet skin images via GAN with Gaussian weighted patch blending R Jiang, B Duke, F Flament, P Aarabi 2022 IEEE International Symposium on Multimedia (ISM), 157-158, 2022 | | 2022 |
| The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation E Wern Teh, T DeVries, B Duke, R Jiang, P Aarabi, GW Taylor arXiv e-prints, arXiv: 2103.17105, 2021 | | 2021 |
Graham TaylorUniversity of Guelph and Vector Institute for Artificial IntelligenceVerified email at uoguelph.ca
