Selected Publications
insafutdinov2022snes.pdfEldar Insafutdinov*, Dylan Campbell*, João F. Henriques, and Andrea Vedaldi [*equal contribution]
SNeS: Learning Probably Symmetric Neural Surfaces from Incomplete Data
The 17th European Conference on Computer Vision (ECCV), Tel Aviv, Israel, 2022
[Website] [Blog] [Paper] [Supplementary Material] [Code]
BibTeX
@article{insafutdinov2022snes,
title={{SNeS:} Learning Probably Symmetric Neural Surfaces from Incomplete Data},
author={Insafutdinov, Eldar and Campbell, Dylan and Henriques, Jo{\~a}o F and Vedaldi, Andrea},
booktitle={European Conference on Computer Vision (ECCV)},
year={2022},
publisher={Springer}
}
BibTeX
@inproceedings{albanie202223,
title={A 23 {MW} data centre is all you need},
author={Albanie, Samuel and Campbell, Dylan and Henriques, Jo{\~a}o F},
booktitle={Special Interest Group on Harry Quantile Bovik (SIGBOVIK)},
year={2022}
}
shi2022accurate.pdfFrederic Z. Zhang, Dylan Campbell, and Stephen Gould
Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer
The 38th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, USA, 2022
[Website] [Paper] [Supplementary Material] [Code] [Video]
BibTeX
@inproceedings{zhang2022efficient,
author = {Zhang, Frederic Z. and Campbell, Dylan and Gould, Stephen},
title = {Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2022},
pages = {20104-20112}
}
gould2022exploiting.pdfStephen Gould, Dylan Campbell, Itzik Ben-Shabat, Chamin Hewa Koneputugodage, and Zhiwei Xu
Exploiting Problem Structure in Deep Declarative Networks: Two Case Studies
The AAAI Conference on Artificial Intelligence Workshops (AAAIW), virtual, 2022
[Paper]
BibTeX
@article{gould2022exploiting,
title={Exploiting Problem Structure in Deep Declarative Networks: Two Case Studies},
author={Gould, Stephen and Campbell, Dylan and Ben-Shabat, Itzik and Koneputugodage, Chamin Hewa and Xu, Zhiwei},
journal={arXiv preprint arXiv:2202.12404},
year={2022}
}
BibTeX
@article{cheraghian2021zero,
title={Zero-shot learning on {3D} point cloud objects and beyond},
author={Cheraghian, Ali and Rahman, Shafinn and Chowdhury, Townim F and Campbell, Dylan and Petersson, Lars},
journal={International Journal of Computer Vision},
year={2021},
publisher={Springer}
}
BibTeX
@article{shi2022accurate,
title={Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching},
author={Shi, Yujiao and Yu, Xin and Liu, Liu and Campbell, Dylan and Koniusz, Piotr and Li, Hongdong},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
year={2022}
}
BibTeX
@article{shi2022geometry,
title={Geometry-guided street-view panorama synthesis from satellite imagery},
author={Shi, Yujiao and Campbell, Dylan and Yu, Xin and Li, Hongdong},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2022},
publisher={IEEE}
}
patrick2021keeping.pdfMandela Patrick*, Dylan Campbell*, Yuki Asano*, Ishan Misra, Florian Metze, Christoph Feichtenhofer, Andrea Vedaldi, and João F. Henriques [*equal contribution]
Keeping your eye on the ball: Trajectory attention in video transformers
Advances in Neural Information Processing Systems (NeurIPS), virtual, 2021 [Oral – 0.6% acceptance rate]
[Paper] [Supplementary Material] [Code]
BibTeX
@inproceedings{patrick2021keeping,
author = {Patrick, Mandela and Campbell, Dylan and Asano, Yuki and Misra, Ishan and Metze, Florian and Feichtenhofer, Christoph and Vedaldi, Andrea and Henriques, Jo\~{a}o F.},
booktitle = {Advances in Neural Information Processing Systems},
editor = {M. Ranzato and A. Beygelzimer and Y. Dauphin and P.S. Liang and J. Wortman Vaughan},
pages = {12493--12506},
publisher = {Curran Associates, Inc.},
title = {Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers},
url = {https://proceedings.neurips.cc/paper/2021/file/67f7fb873eaf29526a11a9b7ac33bfac-Paper.pdf},
volume = {34},
year = {2021}
}
BibTeX
@article{gould2021deep,
title={Deep declarative networks},
author={Gould, Stephen and Hartley, Richard and Campbell, Dylan},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2021},
publisher={IEEE}
}
zhang2021spatially.pdfFrederic Z. Zhang, Dylan Campbell, and Stephen Gould
Spatially conditioned graphs for detecting human-object interactions
The 18th International Conference on Computer Vision (ICCV), virtual, 2021
[Paper] [Supplementary Material] [Code] [Video]
BibTeX
@inproceedings{zhang2021scg,
author = {Frederic Z. Zhang, Dylan Campbell and Stephen Gould},
title = {Spatially Conditioned Graphs for Detecting Human–Object Interactions},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2021},
pages = {13319-13327}
}
BibTeX
@inproceedings{jiang2021learning,
title={Learning to estimate hidden motions with global motion aggregation},
author={Jiang, Shihao and Campbell, Dylan and Lu, Yao and Li, Hongdong and Hartley, Richard},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
pages={9772--9781},
year={2021}
}
shabat2021ikea.pdfYizhak Ben-Shabat, Xin Yu, Fatemeh Saleh, Dylan Campbell, Cristian Rodriguez-Opazo, Hongdong Li, and Stephen Gould
The IKEA ASM Dataset: Understanding people assembling furniture through actions, objects and pose
The IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, USA, 2021
BibTeX
@inproceedings{ben2021ikea,
title={The {IKEA ASM} dataset: Understanding people assembling furniture through actions, objects and pose},
author={Ben-Shabat, Yizhak and Yu, Xin and Saleh, Fatemeh and Campbell, Dylan and Rodriguez-Opazo, Cristian and Li, Hongdong and Gould, Stephen},
booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
pages={847--859},
year={2021}
}
jiang2020joint.pdfShihao Jiang, Dylan Campbell, Miaomiao Liu, Stephen Gould, and Richard Hartley
Joint unsupervised learning of optical flow and egomotion with bi-level optimization
The International Conference on 3D Vision (3DV), virtual, 2020
[Paper]
BibTeX
@inproceedings{jiang2020joint,
title={Joint unsupervised learning of optical flow and egomotion with bi-level optimization},
author={Jiang, Shihao and Campbell, Dylan and Liu, Miaomiao and Gould, Stephen and Hartley, Richard},
booktitle={2020 International Conference on 3D Vision (3DV)},
pages={682--691},
year={2020},
organization={IEEE}
}
campbell2020bpnpnet.pdfDylan Campbell, Liu Liu and Stephen Gould
Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization
The 16th European Conference on Computer Vision (ECCV), Glasgow, UK, 2020 [Oral – 2% acceptance rate]
[Abstract] [Paper] [Supplementary Material] [Code] [arXiv] [Video]
BibTeX
@inproceedings{campbell2020solving,
title={Solving the blind perspective-n-point problem end-to-end with robust differentiable geometric optimization},
author={Campbell, Dylan and Liu, Liu and Gould, Stephen},
booktitle={European Conference on Computer Vision},
pages={244--261},
year={2020},
organization={Springer}
}
BibTeX
@inproceedings{song2020deep,
author="Song, Zhenbo and Chen, Wayne and Campbell, Dylan and Li, Hongdong",
editor="Vedaldi, Andrea and Bischof, Horst and Brox, Thomas and Frahm, Jan-Michael",
title={Deep Novel View Synthesis from Colored 3D Point Clouds},
booktitle={Computer Vision -- ECCV 2020},
year={2020},
publisher={Springer International Publishing},
address={Cham},
pages={1--17},
isbn={978-3-030-58586-0}
}
santacruz2020inferring.pdfRodrigo Santa Cruz, Anoop Cherian, Basura Fernando, Dylan Campbell and Stephen Gould
Inferring Temporal Compositions of Actions Using Probabilistic Automata
The 36th IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, USA, 2020
Workshop on Compositionality in Computer Vision (CICV2020)
BibTeX
@inproceedings{cruz2020inferring,
author = {Cruz, Rodrigo Santa and Cherian, Anoop and Fernando, Basura and Campbell, Dylan and Gould, Stephen},
title = {Inferring Temporal Compositions of Actions Using Probabilistic Automata},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2020}
}
shi2020where.pdfYujiao Shi, Xin Yu, Dylan Campbell and Hongdong Li
Where Am I Looking At? Joint Location and Orientation Estimation by Cross-View Matching
The 36th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, 2020
[Abstract] [Paper] [Supplementary Material] [Code]
BibTeX
@inproceedings{shi2020where,
author = {Shi, Yujiao and Yu, Xin and Campbell, Dylan and Li, Hongdong},
title = {Where Am I Looking At? Joint Location and Orientation Estimation by Cross-View Matching},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}
campbell2019alignment.pdfDylan Campbell, Lars Petersson, Laurent Kneip, Hongdong Li and Stephen Gould
The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation
The 35th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, 2019
[Abstract] [BibTeX] [PDF] [Supplementary Material] [Code] [arXiv]
campbell2018globally.pdfDylan Campbell, Lars Petersson, Laurent Kneip and Hongdong Li
Globally-Optimal Inlier Set Maximisation for Camera Pose and Correspondence Estimation
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018
1st Prize IEEE Australia Council Postgraduate Student Paper Competition
[Abstract] [BibTeX] [PDF] [Supplementary Material] [Code] [Website]
campbell2017globally.pdfDylan Campbell, Lars Petersson, Laurent Kneip and Hongdong Li
Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence
The 16th International Conference on Computer Vision (ICCV), Venice, Italy, 2017 [Oral – 2% acceptance rate]
Marr Prize Honourable Mention
[Abstract] [BibTeX] [PDF] [Supplementary Material] [Original Code] [Code] [Website] [arXiv] [Slides]
campbell2016gogma.pdfDylan Campbell and Lars Petersson
GOGMA: Globally-Optimal Gaussian Mixture Alignment
The 32nd IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 2016 [Spotlight - 10% acceptance rate]
[Abstract] [BibTeX] [PDF] [Supplementary Material] [Code] [Website] [arXiv]
yang2016goicp.pdfJiaolong Yang, Hongdong Li, Dylan Campbell and Yunde Jia
Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016
[Abstract] [BibTeX] [PDF] [Supplementary Material] [Code] [arXiv]
campbell2015metric.pdfDylan Campbell and Mark Whitty
Metric-Based Detection of Robot Kidnapping with an SVM Classifier
Robotics and Autonomous Systems (RAS), 2015
campbell2013metric.pdfDylan Campbell and Mark Whitty
Metric-Based Detection of Robot Kidnapping
The 6th European Conference on Mobile Robots (ECMR), Barcelona, Spain, 2013 [Oral Presentation]
campbell2012mobile.pdfDylan Campbell, Mark Whitty and Samsung Lim
Mobile 3D Indoor Mapping Using the Continuous Normal Distributions Transform
The 3rd International Conference on Indoor Positioning and Indoor Navigation (IPIN), Sydney, Australia, 2012 [Oral]