Jaime Spencer

Postdoc, University of Surrey

Joined

July 2019

Names

Jaime Spencer

Emails

****@surrey.ac.uk (Confirmed)

Personal Links

Career & Education History

Postdoc

University of Surrey (surrey.ac.uk)

2021 – Present

PhD student

University of Surrey (surrey.ac.uk)

2017 – 2022

Undergrad student

University of Surrey (surrey.ac.uk)

2013 – 2017

Advisors, Relations & Conflicts

Postdoc Advisor

Simon Hadfield

2021 – Present

Postdoc Advisor

Richard Bowden

2021 – Present

Expertise

deep feature learning

multi-task learning

monocular depth estimation

2017 – Present

Publications

Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Matter
Jaime Spencer, Chris Russell, Simon Hadfield, Richard Bowden
- Accepted by TMLR
- Readers: Everyone
Medusa: Universal Feature Learning via Attentional Multitasking
Jaime Spencer, Richard Bowden, Simon Hadfield
- 2022 (modified: 02 Nov 2022)
- CVPR Workshops 2022
- Readers: Everyone
DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning
Jaime Spencer, Richard Bowden, Simon Hadfield
- 2020 (modified: 02 Nov 2022)
- CVPR 2020
- Readers: Everyone
Same Features, Different Day: Weakly Supervised Feature Learning for Seasonal Invariance
Jaime Spencer, Richard Bowden, Simon Hadfield
- 2020 (modified: 02 Nov 2022)
- CVPR 2020
- Readers: Everyone
Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation.
Jaime Spencer, Richard Bowden, Simon Hadfield
- 2019 (modified: 10 Nov 2022)
- CVPR2019
- Readers: Everyone
Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation
Jaime Spencer, Richard Bowden, Simon Hadfield
- 2019 (modified: 02 Nov 2022)
- CVPR 2019
- Readers: Everyone
Localisation via Deep Imagination: Learn the Features Not the Map
Jaime Spencer, Oscar Mendez Maldonado, Richard Bowden, Simon Hadfield
- 2018 (modified: 11 Nov 2022)
- ECCV Workshops (5) 2018
- Readers: Everyone

Jaime Spencer

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Matter

Medusa: Universal Feature Learning via Attentional Multitasking

DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning

Same Features, Different Day: Weakly Supervised Feature Learning for Seasonal Invariance

Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation.

Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregation

Localisation via Deep Imagination: Learn the Features Not the Map

Co-Authors