628 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- École Normale Supérieure - PSLFR8 papers
- Institut national de recherche en sciences et technologies du numériqueFR8 papers
- Département d'InformatiqueFR6 papers
- Centre National de la Recherche ScientifiqueFR4 papers
- Czech Technical University in PragueCZ3 papers
- Georgia Institute of TechnologyUS2 papers
- Laboratoire Jean KuntzmannFR2 papers
- New York UniversityUS2 papers
- THOTH: Apprentissage de modèles visuels à partir de données massivesFR2 papers
- Université Paris Sciences et LettresFR2 papers
- Boston UniversityUS1 paper
- CentraleSupélecFR1 paper
15 papers
WALDO: Future Video Synthesis using Object Layer Decomposition and Parametric Flow Prediction
Guillaume Le Moing, Jean Ponce, Cordelia Schmid
This paper presents WALDO (WArping Layer-Decomposed Objects), a novel approach to the prediction of future video frames from past ones. Individual images are decomposed into multip…
Leveraging Randomized Smoothing for Optimal Control of Nonsmooth Dynamical Systems
Quentin Le Lidec, Fabian Schramm, Louis Montaut +3
Optimal control (OC) algorithms such as Differential Dynamic Programming (DDP) take advantage of the derivatives of the dynamics to efficiently control physical systems. Yet, in th…
VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
Adrien Bardes, Jean Ponce, Yann LeCun
Recent self-supervised methods for image representation learning are based on maximizing the agreement between embedding vectors from different views of the same image. A trivial s…
Identifying Heavy-Flavor Jets Using Vectors of Locally Aggregated Descriptors
Jana Bielčíková, Raghav Kunnawalkam Elayavalli, Georgy Ponimatkin +2
Jets of collimated particles serve a multitude of purposes in high energy collisions. Recently, studies of jet interaction with the quark-gluon plasma (QGP) created in high energy…
Neighbourhood Consensus Networks
Ignacio Rocco, Mircea Cimpoi, Relja Arandjelović +3
We address the problem of finding reliable dense correspondences between a pair of images. This is a challenging task due to strong appearance differences between the corresponding…
Compressing the Input for CNNs with the First-Order Scattering Transform
Edouard Oyallon, Eugene Belilovsky, Sergey Zagoruyko +1
We study the first-order scattering transform as a candidate for reducing the signal processed by a convolutional neural network (CNN). We show theoretical and empirical evidence t…
Learning to Localize and Align Fine-Grained Actions to Sparse Instructions
Meera Hahn, Nataniel Ruiz, Jean-Baptiste Alayrac +2
Automatic generation of textual video descriptions that are time-aligned with video content is a long-standing goal in computer vision. The task is challenging due to the difficult…
Modeling Spatio-Temporal Human Track Structure for Action Localization
Guilhem Chéron, Anton Osokin, Ivan Laptev +1
This paper addresses spatio-temporal localization of human actions in video. In order to localize actions in time, we propose a recurrent localization network (RecLNet) designed to…
The THUMOS Challenge on Action Recognition for Videos "in the Wild"
Haroon Idrees, Amir R. Zamir, Yu-Gang Jiang +4
Automatically recognizing and localizing wide ranges of human actions has crucial importance for video understanding. Towards this goal, the THUMOS challenge was introduced in 2013…
Long-term Temporal Convolutions for Action Recognition
Gül Varol, Ivan Laptev, Cordelia Schmid
Typical human actions last several seconds and exhibit characteristic spatio-temporal structure. Recent methods attempt to capture this structure and learn action representations w…
Proposal Flow
Bumsub Ham, Minsu Cho, Cordelia Schmid +1
Finding image correspondences remains a challenging problem in the presence of intra-class variations and large changes in scene layout.~Semantic flow methods are designed to handl…
A General Multi-Graph Matching Approach via Graduated Consistency-regularized Boosting
Junchi Yan, Minsu Cho, Hongyuan Zha +2
This paper addresses the problem of matching weighted graphs referring to an identical object or category. More specifically, matching the common node correspondences among gra…
Segmentation of the mean of heteroscedastic data via cross-validation
Sylvain Arlot, Alain Celisse
This paper tackles the problem of detecting abrupt changes in the mean of a heteroscedastic signal by model selection, without knowledge on the variations of the noise. A new famil…
Risk bounds in linear regression through PAC-Bayesian truncation
Jean-Yves Audibert, Olivier Catoni
We consider the problem of predicting as well as the best linear combination of d given functions in least squares regression, and variants of this problem including constraints on…
Choosing a penalty for model selection in heteroscedastic regression
Sylvain Arlot
We consider the problem of choosing between several models in least-squares regression with heteroscedastic data. We prove that any penalization procedure is suboptimal when the pe…