182 citations
- Technicolor (United States)US18 papers
- Technicolor (France)FR14 papers
- Institut national de recherche en sciences et technologies du numériqueFR6 papers
- Stanford UniversityUS5 papers
- École Polytechnique Fédérale de LausanneCH3 papers
- Max Planck Institute for InformaticsDE3 papers
- Rutgers, The State University of New JerseyUS3 papers
- Centre Inria de l'Université de LilleFR2 papers
- Centre Inria de l'Université de RennesFR2 papers
- Max Planck SocietyDE2 papers
- University of California, BerkeleyUS2 papers
- University of PittsburghUS2 papers
4 papers · 2 filters
VideoMem: Constructing, Analyzing, Predicting Short-term and Long-term Video Memorability
Romain Cohendet, Claire-Hélène Demarty, Ngoc Q. K. Duong +1
Humans share a strong tendency to memorize/forget some of the visual information they encounter. This paper focuses on providing computational models for the prediction of the intr…
A Flexible Convolutional Solver with Application to Photorealistic Style Transfer
Gilles Puy, Patrick Pérez
We propose a new flexible deep convolutional neural network (convnet) to perform fast visual style transfer. In contrast to existing convnets that address the same task, our archit…
Finding beans in burgers: Deep semantic-visual embedding with localization
Martin Engilberge, Louis Chevallier, Patrick Pérez +1
Several works have proposed to learn a two-path neural network that maps images and texts, respectively, to a same shared Euclidean space where geometry captures useful semantic re…
Towards Principled Design of Deep Convolutional Networks: Introducing SimpNet
Seyyed Hossein Hasanpour, Mohammad Rouhani, Mohsen Fayyaz +2
Major winning Convolutional Neural Networks (CNNs), such as VGGNet, ResNet, DenseNet, \etc, include tens to hundreds of millions of parameters, which impose considerable computatio…