Unsupervised Learning from Narrated Instruction Videos

Jean-Baptiste Alayrac 1, 2, 3 Piotr Bojanowski 2, 4 Nishant Agrawal 1, 2, 5 Josef Sivic 4, 2 Ivan Laptev 2 Simon Lacoste-Julien 1, 6, 3
2 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
3 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : We address the problem of automatically learning the main steps to complete a certain task, such as changing a car tire, from a set of narrated instruction videos. The contributions of this paper are three-fold. First, we develop a new unsupervised learning approach that takes advantage of the complementary nature of the input video and the associated narration. The method solves two clustering problems, one in text and one in video, applied one after each other and linked by joint constraints to obtain a single coherent sequence of steps in both modalities. Second, we collect and annotate a new challenging dataset of real-world instruction videos from the Internet. The dataset contains about 800,000 frames for five different tasks that include complex interactions between people and objects, and are captured in a variety of indoor and outdoor settings. Third, we experimentally demonstrate that the proposed method can automatically discover, in an unsupervised manner, the main steps to achieve the task and locate the steps in the input videos.
Type de document :
Communication dans un congrès
CVPR2016 - 29th IEEE Conference on Computer Vision and Pattern Recognition, Jun 2016, Las Vegas, United States. 2016
Liste complète des métadonnées

https://hal.inria.fr/hal-01171193
Contributeur : Jean-Baptiste Alayrac <>
Soumis le : vendredi 3 juillet 2015 - 10:03:01
Dernière modification le : jeudi 11 janvier 2018 - 06:23:26

Identifiants

  • HAL Id : hal-01171193, version 1
  • ARXIV : 1506.09215

Collections

Citation

Jean-Baptiste Alayrac, Piotr Bojanowski, Nishant Agrawal, Josef Sivic, Ivan Laptev, et al.. Unsupervised Learning from Narrated Instruction Videos. CVPR2016 - 29th IEEE Conference on Computer Vision and Pattern Recognition, Jun 2016, Las Vegas, United States. 2016. 〈hal-01171193〉

Partager

Métriques

Consultations de la notice

517