Action Detection from Egocentric Videos in Daily Living Scenarios

G. Kapidis, Elsbeth van Dam, R.W. Poppe, Lucas Noldus, R.C. Veltkamp

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

We are researching the use of egocentric vision in the area of Human Action Recognition. Inspired from recent advances in activity recognition from video using deep learning, we investigate the detection performance of Long Short-Term Memory networks on an elementary set of Activities of Daily Living, based on the detected objects in the scene.
Original languageEnglish
Title of host publicationMeasuring Behavior 2018
Subtitle of host publicationConference Proceedings, 11th International Conference on Methods and Techniques in Behavioral Research, 5 th -8 th June 2018 Manchester Metropolitan University
EditorsRobyn Grant, Tom Allen, Andrew Spink, Matthew Sullivan
Pages405-407
Number of pages3
Publication statusPublished - 2018
EventMeasuring Behavior 2018 - Manchester, United Kingdom
Duration: 5 Jun 20188 Jun 2018

Conference

ConferenceMeasuring Behavior 2018
Abbreviated titleMB2018
Country/TerritoryUnited Kingdom
CityManchester
Period5/06/188/06/18

Fingerprint

Dive into the research topics of 'Action Detection from Egocentric Videos in Daily Living Scenarios'. Together they form a unique fingerprint.

Cite this