P
Piotr Bilinski
Researcher at University of Oxford
Publications - 37
Citations - 902
Piotr Bilinski is an academic researcher from University of Oxford. The author has contributed to research in topics: Computer science & Discriminative model. The author has an hindex of 14, co-authored 31 publications receiving 640 citations. Previous affiliations of Piotr Bilinski include French Institute for Research in Computer Science and Automation & Microsoft.
Papers
More filters
Proceedings ArticleDOI
Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation
TL;DR: This work proposes a novel end-to-end trainable, deep, encoder-decoder architecture for single-pass semantic segmentation based on a cascaded architecture with feature-level long-range skip connections and introduces dense decoder shortcut connections.
Journal ArticleDOI
Multi3Net: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery
Tim G. J. Rudner,Marc Rußwurm,Jakub Fil,Ramona Pelich,Benjamin Bischke,Veronika Kopackova,Piotr Bilinski +6 more
TL;DR: A novel approach for rapid segmentation of flooded buildings by fusing multiresolution, multisensor, and multitemporal satellite imagery in a convolutional neural network that allows for rapid and accurate post-disaster damage assessment and can be used by governments to better coordinate medium- and long-term financial assistance programs for affected areas.
Proceedings ArticleDOI
HRTF magnitude synthesis via sparse representation of anthropometric features
TL;DR: Experiments show that the proposed sparse representation based approach for the synthesis of the magnitudes of Head-related Transfer Functions (HRTFs) outperforms all other evaluated techniques, and that the synthesized HRTFs are almost as good as the best possible HRTF classifier.
Proceedings ArticleDOI
Human violence recognition and detection in surveillance videos
Piotr Bilinski,Francois Bremond +1 more
TL;DR: An extension of the Improved Fisher Vectors for videos is proposed, which allows to represent a video using both local features and their spatio-temporal positions, and makes the violence detection significantly faster.
Proceedings ArticleDOI
ImaGINator: Conditional Spatio-Temporal GAN for Video Generation
TL;DR: A novel conditional GAN architecture, namely ImaGINator, which given a single image, a condition (label of a facial expression or action) and noise, decomposes appearance and motion in both latent and high level feature spaces, generating realistic videos.