Follow
Martin Engelcke
Martin Engelcke
DeepMind
Verified email at deepmind.com
Title
Cited by
Cited by
Year
3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
B Graham, M Engelcke, L van der Maaten
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
7472018
Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networks
M Engelcke, D Rao, DZ Wang, CH Tong, I Posner
IEEE International Conference on Robotics and Automation (ICRA), 2017
4982017
GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
M Engelcke, AR Kosiorek, O Parker Jones, I Posner
International Conference on Learning Representations (ICLR), 2020
1562020
On the Limitations of Representing Functions on Sets
E Wagstaff, FB Fuchs, M Engelcke, I Posner, M Osborne
International Conference on Machine Learning (ICML), 2019
1222019
Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55
L Yi, L Shao, M Savva, H Huang, Y Zhou, Q Wang, B Graham, M Engelcke, ...
arXiv preprint arXiv:1710.06104, 2017
582017
GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement
M Engelcke, OP Jones, I Posner
Advances in Neural Information Processing Systems (NeurIPS), 2021
342021
RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
S Ehrhardt, O Groth, A Monszpart, M Engelcke, I Posner, N Mitra, ...
Advances in Neural Information Processing Systems (NeurIPS), 2020
332020
Analyzing Spatially-Sparse Data Based on Submanifold Sparse Convolutional Neural Networks
BT Graham, LJP van der Maaten, MH Engelcke
US Patent App. 16/193,735, 2019
292019
Universal approximation of functions on sets
E Wagstaff, FB Fuchs, M Engelcke, MA Osborne, I Posner
Journal of Machine Learning Research 23 (151), 1-56, 2022
92022
Reconstruction Bottlenecks in Object-Centric Generative Models
M Engelcke, O Parker Jones, I Posner
Workshop on Object-Oriented Learning at ICML 2020, 2020
92020
A Neural Network and Method of Using a Neural Network to Detect Objects in an Environment
M Engelcke, D Rao, DZ Wang, CH Tong, I Posner
US Patent App. 16/334,815, 2020
92020
APEX: Unsupervised, Object-Centric Scene Segmentation and Tracking for Robot Manipulation
Y Wu, OP Jones, M Engelcke, I Posner
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021
72021
First Steps: Latent-Space Control with Semantic Constraints for Quadruped Locomotion
AL Mitchell, M Engelcke, O Parker Jones, D Surovik, I Havoutis, I Posner
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020
62020
Reaching Through Latent Space: From Joint Statistics to Path Planning in Manipulation
CM Hung, S Zhong, W Goodwin, OP Jones, M Engelcke, I Havoutis, ...
IEEE Robotics and Automation Letters 7 (2), 5334-5341, 2022
12022
Next Steps: Learning a Disentangled Gait Representation for Versatile Quadruped Locomotion
AL Mitchell, W Merkt, M Geisert, S Gangapurwala, M Engelcke, OP Jones, ...
IEEE International Conference on Robotics and Automation (ICRA), 2022
12022
VAE-Loco: Versatile Quadruped Locomotion by Learning a Disentangled Gait Representation
AL Mitchell, W Merkt, M Geisert, S Gangapurwala, M Engelcke, OP Jones, ...
arXiv preprint arXiv:2205.01179, 2022
2022
Efficient Object Detection and Discovery for Real-World Robotics Applications
M Engelcke
University of Oxford, 2020
2020
The system can't perform the operation now. Try again later.
Articles 1–17