Unsupervised Learning from Narrated Instruction Videos

Authors:
  • JAJean-Baptiste Alayrac
    Jean-Baptiste Alayrac
  • PBPiotr Bojanowski
    Piotr Bojanowski
  • NANishant Agrawal
    Nishant Agrawal
  • JSJosef Sivic
    Josef Sivic
  • ILIvan Laptev
    Ivan Laptev
  • SLSimon Lacoste-Julien
    Simon Lacoste-Julien
Publisher website
Google Scholar
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 tasks1 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.

This publication has 18 references indexed in Scilit: