| Back to basics: Unsupervised learning of optical flow via brightness constancy and motion smoothness JJ Yu, AW Harley, KG Derpanis Computer Vision–ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8 …, 2016 | 443 | 2016 |
| Evaluation of deep convolutional nets for document image classification and retrieval AW Harley, A Ufkes, KG Derpanis 2015 13th International Conference on Document Analysis and Recognition …, 2015 | 357 | 2015 |
| An interactive node-link visualization of convolutional neural networks AW Harley Advances in Visual Computing: 11th International Symposium, ISVC 2015, Las …, 2015 | 170 | 2015 |
| Adversarial inverse graphics networks: Learning 2d-to-3d lifting and image-to-image translation from unpaired supervision HY Fish Tung, AW Harley, W Seto, K Fragkiadaki Proceedings of the IEEE International Conference on Computer Vision, 4354-4362, 2017 | 164 | 2017 |
| Segmentation-aware convolutional networks using local attention masks AW Harley, KG Derpanis, I Kokkinos Proceedings of the IEEE International Conference on Computer Vision, 5038-5047, 2017 | 162 | 2017 |
| Vr facial animation via multiview image translation SE Wei, J Saragih, T Simon, AW Harley, S Lombardi, M Perdoch, A Hypes, ... ACM Transactions on Graphics (TOG) 38 (4), 1-16, 2019 | 119 | 2019 |
| Reward learning from narrated demonstrations HY Tung, AW Harley, LK Huang, K Fragkiadaki Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2018 | 36 | 2018 |
| Particle video revisited: Tracking through occlusions using point trajectories AW Harley, Z Fang, K Fragkiadaki European Conference on Computer Vision, 59-75, 2022 | 27 | 2022 |
| Learning from unlabelled videos using contrastive predictive neural 3d mapping AW Harley, SK Lakshmikanth, F Li, X Zhou, HYF Tung, K Fragkiadaki arXiv preprint arXiv:1906.03764, 2019 | 27* | 2019 |
| Learning dense convolutional embeddings for semantic segmentation AW Harley, KG Derpanis, I Kokkinos arXiv preprint arXiv:1511.04377, 2015 | 24 | 2015 |
| Simple-BEV: What really matters for multi-sensor bev perception? AW Harley, Z Fang, J Li, R Ambrus, K Fragkiadaki 2023 IEEE International Conference on Robotics and Automation (ICRA), 2759-2765, 2023 | 19 | 2023 |
| CoCoNets: Continuous contrastive 3D scene representations S Lal, M Prabhudesai, I Mediratta, AW Harley, K Fragkiadaki Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2021 | 19 | 2021 |
| Tidee: Tidying up novel rooms using visuo-semantic commonsense priors G Sarch, Z Fang, AW Harley, P Schydlo, MJ Tarr, S Gupta, K Fragkiadaki European Conference on Computer Vision, 480-496, 2022 | 15 | 2022 |
| Move to see better: Self-improving embodied object detection Z Fang, A Jain, G Sarch, AW Harley, K Fragkiadaki arXiv preprint arXiv:2012.00057, 2020 | 15 | 2020 |
| Embodied language grounding with 3d visual feature representations M Prabhudesai, HYF Tung, SA Javed, M Sieb, AW Harley, K Fragkiadaki Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020 | 13 | 2020 |
| Disentangling 3d prototypical networks for few-shot concept learning M Prabhudesai, S Lal, D Patil, HY Tung, AW Harley, K Fragkiadaki arXiv preprint arXiv:2011.03367, 2020 | 12 | 2020 |
| A simple baseline for bev perception without lidar AW Harley, Z Fang, J Li, R Ambrus, K Fragkiadaki arXiv e-prints, arXiv: 2206.07959, 2022 | 11 | 2022 |
| Adversarial inversion: Inverse graphics with adversarial priors HYF Tung, A Harley, W Seto, K Fragkiadaki arXiv preprint arXiv:1705.11166 3, 2017 | 10 | 2017 |
| Embodied language grounding with implicit 3d visual feature representations M Prabhudesai, HYF Tung, SA Javed, M Sieb, AW Harley, K Fragkiadaki | 9 | 2019 |
| Tracking emerges by looking around static scenes, with neural 3d mapping AW Harley, SK Lakshmikanth, P Schydlo, K Fragkiadaki Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23 …, 2020 | 8 | 2020 |
Katerina FragkiadakiAssistant Professor, Carnegie Mellon UniversityAdresă de e-mail confirmată pe cs.cmu.edu
