An Exocentric Look At Egocentric Actions And Vice Versa

Keywords

Action recognition; Egocentric vision; Transfer learning

Abstract

In this work we address the task of relating action information across two drastically different visual domains, namely, first-person (egocentric) and third-person (exocentric). We investigate two different yet highly interconnected problems including cross-view action classification and action based video retrieval. First, we perform action classification in one domain using the knowledge transferred from the other domain. Second, given a video in one view, we retrieve videos from the same action class in the other view. In order to evaluate our models, we collect a new cross-domain dataset of egocentric-exocentric action videos containing 14 action classes and 3569 videos (1676 collected egocentric videos and 1893 exocentric videos borrowed from the UCF 101 dataset). Our results demonstrate the possibility of transferring action information across the two domains and suggest new directions in relating first and third person vision for other tasks.

Publication Date

6-1-2018

Publication Title

Computer Vision and Image Understanding

Volume

171

Number of Pages

61-68

Document Type

Article

Personal Identifier

scopus

DOI Link

https://doi.org/10.1016/j.cviu.2018.05.005

Socpus ID

85047566183 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85047566183

This document is currently not available here.

Share

COinS