The Instantaneous Accuracy: A Novel Metric for the Problem of Online Human Behaviour Recognition in Untrimmed Videos

Marcos Baptista Ríos, Roberto J. Lopez-Sastre, Fabian Caba Heilbron, Jan van Gemert

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

2 Citations (Scopus)

Abstract

The problem of Online Human Behavior Recognition in untrimmed videos, aka Online Action Detection (OAD), needs to be revisited. Unlike traditional off-line action detection approaches, where the evaluation metrics are clear and well established, in the OAD setting we find few works and no consensus on evaluation protocols to be used. In this paper we introduce a novel online metric, the Instantaneous Accuracy (IA), that exhibits an online nature, solving most of the limitations of the previous (off-line) metrics. We conduct a thorough experimental evaluation on the TVSeries dataset, comparing the performance of various baseline methods with the state of the art. Our results confirm the problems of the previous evaluation protocols, and suggest that an IA-based protocol is more adequate to the online scenario for human behaviour understanding.
Original languageEnglish
Title of host publicationProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
Pages1282-1284
Number of pages3
ISBN (Electronic)978-1-7281-5023-9
DOIs
Publication statusPublished - 2019
Event2019 ICCV workshop on Human Behavior Understanding - Seoul, Korea, Democratic People's Republic of
Duration: 27 Oct 201927 Oct 2019

Publication series

NameProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

Workshop

Workshop2019 ICCV workshop on Human Behavior Understanding
Country/TerritoryKorea, Democratic People's Republic of
CitySeoul
Period27/10/1927/10/19

Keywords

  • Evaluation protocols
  • Online action detection
  • Untrimmed videos

Fingerprint

Dive into the research topics of 'The Instantaneous Accuracy: A Novel Metric for the Problem of Online Human Behaviour Recognition in Untrimmed Videos'. Together they form a unique fingerprint.

Cite this