455 citations
- Centre National de la Recherche ScientifiqueFR16 papers
- Institut national de recherche en sciences et technologies du numériqueFR14 papers
- Télécom ParisFR10 papers
- SupélecFR9 papers
- Institut de Recherche en Informatique et Systèmes AléatoiresFR7 papers
- Université de RennesFR7 papers
- Institut d'Électronique et des Technologies du numéRiqueFR5 papers
- Institut Polytechnique de ParisFR5 papers
- Université Paris 1 Panthéon-SorbonneFR5 papers
- Centre de Recherche en InformatiqueFR4 papers
- IMT AtlantiqueFR4 papers
- Institut Mines-TélécomFR4 papers
13 papers · 1 filter
Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks
Corentin Kervadec, Grigory Antipov, Moez Baccouche +1
The large adoption of the self-attention (i.e. transformer model) and BERT-like training principles has recently resulted in a number of high performing models on a large panoply o…
Towards a General Model of Knowledge for Facial Analysis by Multi-Source Transfer Learning
Valentin Vielzeuf, Alexis Lechervy, Stéphane Pateux +1
This paper proposes a step toward obtaining general models of knowledge for facial analysis, by addressing the question of multi-source transfer learning. More precisely, the propo…
Adapting a FrameNet Semantic Parser for Spoken Language Understanding Using Adversarial Learning
Gabriel Marzinotto, Geraldine Damnati, Frédéric Béchet
This paper presents a new semantic frame parsing model, based on Berkeley FrameNet, adapted to process spoken documents in order to perform information extraction from broadcast co…
MaskParse@Deskin at SemEval-2019 Task 1: Cross-lingual UCCA Semantic Parsing using Recursive Masked Sequence Tagging
Gabriel Marzinotto, Johannes Heinecke, Geraldine Damnati
This paper describes our recursive system for SemEval-2019 \textit{ Task 1: Cross-lingual Semantic Parsing with UCCA}. Each recursive step consists of two parts. We first perform s…
Distributed Power Control with Partial Channel State Information: Performance Characterization and Design
Chao Zhang, Samson Lasaulce, Achal Agrawal +1
One of the goals of this paper is to contribute to finding distributed power control strategies which exploit efficiently the information available about the global channel state;…
TSRuleGrowth : Extraction de règles de prédiction semi-ordonnées à partir d'une série temporelle d'éléments discrets, application dans un contexte d'intelligence ambiante
Benoit Vuillemin, Lionel Delphin-Poulat, Rozenn Nicol +2
This paper presents a new algorithm: TSRuleGrowth, looking for partially-ordered rules over a time series. This algorithm takes principles from the state of the art of rule mining…