no code implementations • 18 Apr 2020 • Clint Sebastian, Raffaele Imbriaco, Egor Bondarev, Peter H. N. de With
In contrast, our work concentrates on re-ranking and embedding expansion techniques.
no code implementations • 15 Apr 2020 • Clint Sebastian, Raffaele Imbriaco, Egor Bondarev, Peter H. N. de With
Building extraction from aerial images has several applications in problems such as urban planning, change detection, and disaster management.
no code implementations • 13 Jan 2020 • Clint Sebastian, Raffaele Imbriaco, Egor Bondarev, Peter H. N. de With
We also perform ablation studies to understand the impact of the adversarial loss.
no code implementations • CVPR 2019 • Ries Uittenbogaard, Clint Sebastian, Julien Vijverberg, Bas Boom, Dariu M. Gavrila, Peter H. N. de With
The current paradigm in privacy protection in street-view images is to detect and blur sensitive information.
no code implementations • 22 Mar 2019 • Raffaele Imbriaco, Clint Sebastian, Egor Bondarev, Peter H. N. de With
In this paper, we present an image retrieval pipeline that uses attentive, local convolutional features and aggregates them using the Vector of Locally Aggregated Descriptors (VLAD) to produce a global descriptor.
no code implementations • 13 Mar 2019 • Clint Sebastian, Bas Boom, Egor Bondarev, Peter H. N. de With
We propose a system that is cost-effective even after increasing the resolution by a factor of 2. 5.
no code implementations • 13 Mar 2019 • Raffaele Imbriaco, Clint Sebastian, Egor Bondarev, Peter de With
The matching of the query image is obtained with a recall@5 larger than 90% for panorama-to-panorama matching.
no code implementations • 8 Oct 2018 • Clint Sebastian, Bas Boom, Thijs van Lankveld, Egor Bondarev, Peter H. N. de With
Detection of buildings and other objects from aerial images has various applications in urban planning and map making.
no code implementations • 5 Sep 2018 • Clint Sebastian, Ries Uittenbogaard, Julien Vijverberg, Bas Boom, Peter H. N. de With
We have performed detection and classification tests across a large number of traffic sign classes, by training the detector using the combination of real and generated data.