Skip to Main content Skip to Navigation
Conference papers

Scene semantics from long-term observation of people

Vincent Delaitre 1 David Fouhey 2 Ivan Laptev 3 Josef Sivic 3 Abhinav Gupta 2 Alexei A. Efros 2
3 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : 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.
Document type :
Conference papers
Complete list of metadata

Cited literature [32 references]  Display  Hide  Download

https://hal.inria.fr/hal-01060880
Contributor : Vincent Delaitre <>
Submitted on : Thursday, September 4, 2014 - 2:31:38 PM
Last modification on : Thursday, July 1, 2021 - 5:58:07 PM
Long-term archiving on: : Friday, December 5, 2014 - 10:28:29 AM

File

delaitre_ECCV12.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Vincent Delaitre, David 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⟩

Share

Metrics

Record views

655

Files downloads

828