Cross-task weakly supervised learning from instructional videos - ENS - École normale supérieure Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Cross-task weakly supervised learning from instructional videos

Résumé

In this paper we investigate learning visual models for the steps of ordinary tasks using weak supervision via instructional narrations and an ordered list of steps instead of strong supervision via temporal annotations. At the heart of our approach is the observation that weakly supervised learning may be easier if a model shares components while learning different steps: "pour egg" should be trained jointly with other tasks involving "pour" and "egg". We formalize this in a component model for recognizing steps and a weakly supervised learning framework that can learn this model under temporal constraints from narration and the list of steps. Past data does not permit systematic studying of sharing and so we also gather a new dataset, CrossTask, aimed at assessing cross-task sharing. Our experiments demonstrate that sharing across tasks improves performance, especially when done at the component level and that our component model can parse previously unseen tasks by virtue of its compositionality.
Fichier principal
Vignette du fichier
paper.pdf (5 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02434806 , version 1 (10-01-2020)

Identifiants

  • HAL Id : hal-02434806 , version 1

Citer

Dimitri Zhukov, Jean-Baptiste Alayrac, Ramazan Gokberk Cinbis, David F. Fouhey, Ivan Laptev, et al.. Cross-task weakly supervised learning from instructional videos. CVPR 2019 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2019, Long Beach, CA, United States. ⟨hal-02434806⟩
43 Consultations
51 Téléchargements

Partager

Gmail Facebook X LinkedIn More