Scene semantics from long-term observation of people - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2012

Scene semantics from long-term observation of people


Our everyday objects support various tasks and can be used by people for different purposes. While object classification is a widely studied topic in computer vision, recognition of object function, i.e., what people can do with an object and how they do it, is rarely addressed. In this paper we construct a functional object description with the aim to recognize objects by the way people interact with them. We describe scene objects (sofas, tables, chairs) by associated human poses and object appearance. Our model is learned discriminatively from automatically estimated body poses in many realistic scenes. In particular, we make use of time-lapse videos from YouTube providing a rich source of common human-object interactions and minimizing the effort of manual object annotation. We show how the models learned from human observations significantly improve object recognition and enable prediction of characteristic human poses in new scenes. Results are shown on a dataset of more than 400,000 frames obtained from 146 time-lapse videos of challenging and realistic indoor scenes.
Fichier principal
Vignette du fichier
delaitre_ECCV12.pdf (2.67 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01060880 , version 1 (04-09-2014)



Vincent Delaitre, David F. Fouhey, Ivan Laptev, Josef Sivic, Abhinav Gupta, et al.. Scene semantics from long-term observation of people. European Conference on Computer Vision, Oct 2012, Florence, Italy. pp.284-298, ⟨10.1007/978-3-642-33783-3_21⟩. ⟨hal-01060880⟩
314 View
327 Download



Gmail Facebook Twitter LinkedIn More