back to funding overview.

Faculty Research Award (Crossview Convolutional Networks)

Overview

This project seeks to develop deep convolutional neural networks that can combine ground-level and overhead imagery for remote sensing tasks. We are exploring several approaches. See below for work that was supported by this award.

Related Publication(s)

  1. Workman S., Zhai M., Crandall D., Jacobs N. 2017. A Unified Model for Near/Remote Sensing. In: IEEE International Conference on Computer Vision (ICCV). website bibtex
  2. Workman S., Souvenir R., Jacobs N. 2017. Understanding and Mapping Natural Beauty. In: IEEE International Conference on Computer Vision (ICCV). website bibtex
  3. PDF Zhai M., Bessinger Z., Workman S., Jacobs N. 2017. Predicting Ground-Level Scene Layout from Aerial Imagery. In: IEEE Computer Vision and Pattern Recognition (CVPR). bibtex
  4. Jacobs N., Workman S., Zhai M. 2016. Crossview Convolutional Networks. In: IEEE Applied Imagery and Pattern Recognition (AIPR). bibtex

Acknowledgements

This work was supported by a Google Faculty Research Award.