Jean-Baptiste Alayrac

is this you? claim profile

0 followers
Google ∙ Inria

Self-Supervised MultiModal Versatile Networks

Videos are a rich source of multi-modal supervision. In this work, we le...
06/29/2020 ∙ by Jean-Baptiste Alayrac, et al. ∙ 82 ∙ share

read it
Learning to Segment Actions from Observation and Narration

We apply a generative segmental model of task structure, guided by narra...
05/07/2020 ∙ by Daniel Fried, et al. ∙ 4 ∙ share

read it
Visual Grounding in Video for Unsupervised Word Translation

There are thousands of actively spoken languages on Earth, but a single ...
03/11/2020 ∙ by Gunnar A. Sigurdsson, et al. ∙ 8 ∙ share

read it
End-to-End Learning of Visual Representations from Uncurated Instructional Videos

Annotating videos is cumbersome, expensive and not scalable. Yet, many s...
12/13/2019 ∙ by Antoine Miech, et al. ∙ 35 ∙ share

read it
Controllable Attention for Structured Layered Video Decomposition

The objective of this paper is to be able to separate a video into its n...
10/24/2019 ∙ by Jean-Baptiste Alayrac, et al. ∙ 24 ∙ share

read it
HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips

Learning text-video embeddings usually requires a dataset of video clips...
06/07/2019 ∙ by Antoine Miech, et al. ∙ 1 ∙ share

read it
Are Labels Required for Improving Adversarial Robustness?

Recent work has uncovered the interesting (and somewhat surprising) find...
05/31/2019 ∙ by Jonathan Uesato, et al. ∙ 0 ∙ share

read it
Cross-task weakly supervised learning from instructional videos

In this paper we investigate learning visual models for the steps of ord...
03/19/2019 ∙ by Dimitri Zhukov, et al. ∙ 4 ∙ share

read it
The Visual Centrifuge: Model-Free Layered Video Representations

True video understanding requires making sense of non-lambertian scenes ...
12/04/2018 ∙ by Jean-Baptiste Alayrac, et al. ∙ 2 ∙ share

read it
Learning to Localize and Align Fine-Grained Actions to Sparse Instructions

Automatic generation of textual video descriptions that are time-aligned...
09/22/2018 ∙ by Meera Hahn, et al. ∙ 6 ∙ share

read it
A flexible model for training action localization with varying levels of supervision

Spatio-temporal action detection in videos is typically addressed in a f...
06/29/2018 ∙ by Guilhem Chéron, et al. ∙ 2 ∙ share

read it
Learning from Video and Text via Large-Scale Discriminative Clustering

Discriminative clustering has been successfully applied to a number of w...
07/27/2017 ∙ by Antoine Miech, et al. ∙ 0 ∙ share

read it
SEARNN: Training RNNs with Global-Local Losses

We propose SEARNN, a novel training algorithm for recurrent neural netwo...
06/14/2017 ∙ by Rémi Leblond, et al. ∙ 0 ∙ share

read it
Joint Discovery of Object States and Manipulation Actions

Many human activities involve object manipulations aiming to modify the ...
02/09/2017 ∙ by Jean-Baptiste Alayrac, et al. ∙ 0 ∙ share

read it
Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs

In this paper, we propose several improvements on the block-coordinate F...
05/30/2016 ∙ by Anton Osokin, et al. ∙ 0 ∙ share

read it
Unsupervised Learning from Narrated Instruction Videos

We address the problem of automatically learning the main steps to compl...
06/30/2015 ∙ by Jean-Baptiste Alayrac, et al. ∙ 0 ∙ share

read it

Jean-Baptiste Alayrac

Featured Co-authors

Andrew Zisserman

Pushmeet Kohli

Cordelia Schmid

Chris Dyer

Simon Lacoste-Julien

Phil Blunsom

Ivan Laptev

James M. Rehg

Josef Sivic

Mateusz Malinowski

Piotr Bojanowski

Self-Supervised MultiModal Versatile Networks

Learning to Segment Actions from Observation and Narration

Visual Grounding in Video for Unsupervised Word Translation

End-to-End Learning of Visual Representations from Uncurated Instructional Videos

Controllable Attention for Structured Layered Video Decomposition

HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips

Are Labels Required for Improving Adversarial Robustness?

Cross-task weakly supervised learning from instructional videos

The Visual Centrifuge: Model-Free Layered Video Representations

Learning to Localize and Align Fine-Grained Actions to Sparse Instructions

A flexible model for training action localization with varying levels of supervision

Learning from Video and Text via Large-Scale Discriminative Clustering

SEARNN: Training RNNs with Global-Local Losses

Joint Discovery of Object States and Manipulation Actions

Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs

Unsupervised Learning from Narrated Instruction Videos