Learning grimaces by watching TVReport as inadecuate

Learning grimaces by watching TV - Download this document for free, or read online. Document in PDF available to download.

Reference: Albanie, S and Vedaldi, A, (2016). Learning grimaces by watching TV.Citable link to this page:


Learning grimaces by watching TV

Abstract: Differently from computer vision systems which require explicit supervision, humans can learn facial expressions by observing people in their environment. In this paper, we look at how similar capabilities could be developed in machine vision. As a starting point, we consider the problem of relating facial expressions to objectively-measurable events occurring in videos. In particular, we consider a gameshow in which contestants play to win significant sums of money. We extract events affecting the game and corresponding facial expressions objectively and automatically from the videos, obtaining large quantities of labelled data for our study. We also develop, using benchmarks such as FER and SFEW 2.0, state-of-the-art deep neural networks for facial expression recognition, showing that pre-training on face verification data can be highly beneficial for this task. Then, we extend these models to use facial expressions to predict events in videos and learn nameable expressions from them. The dataset and emotion recognition models are available at http://www.robots.ox.ac.uk/~vgg/data/facevalue.

Publication status:PublishedPeer Review status:Peer reviewedVersion:Publisher's versionDate of acceptance:2016-05-13 Funder: Engineering and Physical Sciences Research Council   Funder: European Research Council   Notes:© 2016. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.

Bibliographic Details

Publisher: British Machine Vision Association and Society for Pattern Recognition

Publisher Website: http://www.bmva.org/

Host: British Machine Vision Conference 2016see more from them

Publication Website: http://www.bmva.org/bmvc/2016/toc.html

Issue Date: 2016-09Identifiers

Uuid: uuid:95f32db6-45df-4603-b0c0-084b29b26f82

Urn: uri:95f32db6-45df-4603-b0c0-084b29b26f82

Pubs-id: pubs:656200 Item Description

Type: conference-proceeding;

Version: Publisher's version


Author: Albanie, S - Oxford, MPLS, Engineering Science - - - Vedaldi, A - Oxford, MPLS, Engineering Science - - - - Bibliographic Details

Source: https://ora.ox.ac.uk/objects/uuid:95f32db6-45df-4603-b0c0-084b29b26f82


Related documents