Localisation via Deep Imagination: Learn the Features Not the mAP

Jaime Spencer, Oscar Mendez, Richard Bowden, Simon Hadfield

ECCVW 2018 pp. 710-726

doi:10.1007/978-3-030-11021-5_44 /eccvw/2018/spencer2018eccvw-localisation/

Abstract

How many times does a human have to drive through the same area to become familiar with it? To begin with, we might first build a mental model of our surroundings. Upon revisiting this area, we can use this model to extrapolate to new unseen locations and imagine their appearance.

PDF ECCVW Semantic Scholar

Cite

Text

Spencer et al. "Localisation via Deep Imagination: Learn the Features Not the mAP." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11021-5_44

Markdown

[Spencer et al. "Localisation via Deep Imagination: Learn the Features Not the mAP." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/spencer2018eccvw-localisation/) doi:10.1007/978-3-030-11021-5_44

BibTeX

@inproceedings{spencer2018eccvw-localisation,
  title     = {{Localisation via Deep Imagination: Learn the Features Not the mAP}},
  author    = {Spencer, Jaime and Mendez, Oscar and Bowden, Richard and Hadfield, Simon},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2018},
  pages     = {710-726},
  doi       = {10.1007/978-3-030-11021-5_44},
  url       = {https://mlanthology.org/eccvw/2018/spencer2018eccvw-localisation/}
}