Concept
Component video
Related publications (54)
Timelapse: Rhone mouth in Geneva Lake - 2017
The dataset is a collection of RGB and thermal images of the Rhone mouth in Geneva Lake, taken every minute in 2017. ...
EPFL Infoscience2023Timelapse: Geneva Lake, in front of Chexbres - 2019
The dataset is a collection of RGB and thermal images of the Rhone mouth in Geneva Lake, taken every minute in 2019. ...
EPFL Infoscience2023Timelapse: Rhone mouth in Geneva Lake - 2019
The dataset is a collection of RGB and thermal images of the Rhone mouth in Geneva Lake, taken every minute in 2019. ...
EPFL Infoscience2023Timelapse: Rhone mouth in Geneva Lake - 2021
The dataset is a collection of RGB and thermal images of the Rhone mouth in Geneva Lake, taken every minute in 2021. ...
EPFL Infoscience2023Timelapse: Rhone mouth in Geneva Lake - 2023
The dataset is a collection of RGB and thermal images of the Rhone mouth in Geneva Lake, taken every minute from January to August 2023. ...
EPFL Infoscience2023Timelapse: Rhone mouth in Geneva Lake - 2022
The dataset is a collection of RGB and thermal images of the Rhone mouth in Geneva Lake, taken every minute in 2022. ...
EPFL Infoscience2023MultiMAE: Multi-modal Multi-task Masked Autoencoders
Amir Roshan Zamir, Roman Christian Bachmann, David Mizrahi, Andrei Atanov
We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input besides the RGB ...
SPRINGER INTERNATIONAL PUBLISHING AG2022AI-based telepresence for broadcast applications
Touradj Ebrahimi, Rayan Daod Nathoo, Laurent Deillon, Henrique Piñeiro Monteagudo
In this paper, we introduce a new solution and underlying architecture that allows remote participants to interact with hosts in a broadcast scenario. To achieve this, background extraction is first applied to video received from remote participants to ext ...
SPIE2022Human Detection and Segmentation via Multi-view Consensus
Pascal Fua, Mathieu Salzmann, Isinsu Katircioglu, Helge Jochen Rhodin
Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data. However, existing approaches predominantly rely on restrictive assumptions on appearance and motion. For scenes with dynamic activities and ...
IEEE2021NTIRE 2018 Challenge on Spectral Reconstruction from RGB Images
Bing Zhang, Lei Zhang, Majed El Helou, Dong Liu, Ruofan Zhou, Fayez Lahoud, Marjan Shahpaski, Radu Timofte, Chang Chen, Soumik Sarkar, Himanshu Sharma, Yigit Baran Can
This paper reviews the first challenge on spectral image reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3channel RGB image. The challenge was divided into 2 tracks: the "Clean" track sought HS recove ...
IEEE2018