Predicting Actions from Static Scenes - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Predicting Actions from Static Scenes

Abstract

Human actions naturally co-occur with scenes. In this work we aim to discover action-scene correlation for a large number of scene categories and to use such correlation for action prediction. Towards this goal, we collect a new SUN Action dataset with manual annotations of typical human actions for 397 scenes. We next discover action-scene associations and demonstrate that scene categories can be well identified from their associated actions. Using discovered associations, we address a new task of predicting human actions for images of static scenes. We evaluate prediction of 23 and 38 action classes for images of indoor and outdoor scenes respectively and show promising results. We also propose a new application of geo-localized action prediction and demonstrate ability of our method to automatically answer queries such as "Where is a good place for a picnic?" or "Can I cycle along this path?".
Fichier principal
Vignette du fichier
eccv14_actionsfromscenes.pdf (8.26 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01053935 , version 1 (25-08-2014)

Identifiers

Cite

Tuan-Hung Vu, Catherine Olsson, Ivan Laptev, Aude Oliva, Josef Sivic. Predicting Actions from Static Scenes. ECCV'14 - 13th European Conference on Computer Vision, Sep 2014, Zurich, Switzerland. pp.421-436, ⟨10.1007/978-3-319-10602-1_28⟩. ⟨hal-01053935⟩
198 View
636 Download

Altmetric

Share

Gmail Facebook X LinkedIn More