Elliot Crowley

Orcid: 0000-0001-5685-4724

Affiliations:
  • University of Edinburgh, School of Engineering, UK
  • University of Oxford, UK (PhD 2016)


According to our database1, Elliot Crowley authored at least 34 papers between 2013 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Neural Architecture Search as Program Transformation Exploration.
Commun. ACM, October, 2024

einspace: Searching for Neural Architectures from Fundamental Operations.
CoRR, 2024

Hyperparameter Selection in Continual Learning.
CoRR, 2024

EgoPoseFormer: A Simple Baseline for Egocentric 3D Human Pose Estimation.
CoRR, 2024

PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition.
CoRR, 2024

WidthFormer: Toward Efficient Transformer-based BEV View Transformation.
CoRR, 2024

Plug and Play Active Learning for Object Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
DLAS: An Exploration and Assessment of the Deep Learning Acceleration Stack.
CoRR, 2023

Generate Your Own Scotland: Satellite Image Generation Conditioned on Maps.
CoRR, 2023

GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022
Prediction-Guided Distillation for Dense Object Detection.
Proceedings of the Computer Vision - ECCV 2022, 2022

2021
Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning.
CoRR, 2021

Substituting Convolutions for Neural Network Compression.
IEEE Access, 2021

Neural Architecture Search without Training.
Proceedings of the 38th International Conference on Machine Learning, 2021

2020
Neural Architecture Search without Training.
CoRR, 2020

Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget.
Proceedings of the 8th International Conference on Learning Representations, 2020

Optimizing Grouped Convolutions on Edge Devices.
Proceedings of the 31st IEEE International Conference on Application-specific Systems, 2020

2019
Deep Kernel Transfer in Gaussian Processes for Few-shot Learning.
CoRR, 2019

BlockSwap: Fisher-guided Block Substitution for Network Compression.
CoRR, 2019

Separable Layers Enable Structured Efficient Linear Substitutions.
CoRR, 2019

Performance Aware Convolutional Neural Network Channel Pruning for Embedded GPUs.
Proceedings of the IEEE International Symposium on Workload Characterization, 2019

2018
Dilated DenseNets for Relational Reasoning.
CoRR, 2018

HAKD: Hardware Aware Knowledge Distillation.
CoRR, 2018

Pruning neural networks: is it time to nip it in the bud?
CoRR, 2018

CINIC-10 is not ImageNet or CIFAR-10.
CoRR, 2018

Moonshine: Distilling with Cheap Convolutions.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks.
Proceedings of the 2018 IEEE International Symposium on Workload Characterization, 2018

2016
Visual recognition in art using machine learning.
PhD thesis, 2016

The Art of Detection.
Proceedings of the Computer Vision - ECCV 2016 Workshops, 2016

2015
Face Painting: querying art with photos.
Proceedings of the British Machine Vision Conference 2015, 2015

2014
In Search of Art.
Proceedings of the Computer Vision - ECCV 2014 Workshops, 2014

The State of the Art: Object Retrieval in Paintings using Discriminative Regions.
Proceedings of the British Machine Vision Conference, 2014

2013
Of Gods and Goats: Weakly Supervised Learning of Figurative Art.
Proceedings of the British Machine Vision Conference, 2013


  Loading...