Actor and Observer: Joint Modeling of First and Third-Person Videos - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

Actor and Observer: Joint Modeling of First and Third-Person Videos

(1) , (1) , (2) , (3) , (2)
1
2
3

Abstract

Several theories in cognitive neuroscience suggest that when people interact with the world, or simulate interactions, they do so from a first-person egocentric perspective, and seamlessly transfer knowledge between third-person (observer) and first-person (actor). Despite this, learning such models for human action recognition has not been achievable due to the lack of data. This paper takes a step in this direction, with the introduction of Charades-Ego, a large-scale dataset of paired first-person and third-person videos, involving 112 people, with 4000 paired videos. This enables learning the link between the two, actor and observer perspectives. Thereby, we address one of the biggest bottlenecks facing egocentric vision research, providing a link from first-person to the abundant third-person data on the web. We use this data to learn a joint representation of first and third-person videos, with only weak supervision, and show its effectiveness for transferring knowledge from the third-person to the first-person domain.
Fichier principal
Vignette du fichier
Sigurdsson18.pdf (6.71 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01755547 , version 1 (30-03-2018)

Identifiers

Cite

Gunnar A. Sigurdsson, Abhinav Gupta, Cordelia Schmid, Ali Farhadi, Karteek Alahari. Actor and Observer: Joint Modeling of First and Third-Person Videos. CVPR 2018 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2018, Salt Lake City, Utah, United States. pp.7396-7404, ⟨10.1109/CVPR.2018.00772⟩. ⟨hal-01755547⟩
488 View
397 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More