Strategic Pairwise Selection for Labeling High-Risk Action from Video-Based Data

Kuan Ting Chen, Bo Heng Chen, Kun Ta Chuang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Accidental risk can occur anywhere in daily life, with typical examples including pedestrian accidents and concerns about child safety on school campuses. In response to these risks, the field of dangerous behavior detection technology has gained considerable attention. Such technology aims to minimize response times and mitigate the occurrence of harm through early detection of potentially dangerous behavior. However, when it comes to generating label data for these models, the diversity of human behavior and the subjective nature of defining dangerous behaviors make the labeling process challenging, often leading to ambiguous situations. To overcome this challenge, we introduce a labeling generation framework based on pair comparison called Strategic Pair Selection (SPS). SPS employs a comparative approach to assist annotators in determining ambiguous cases, thus enhancing the accuracy of the detection of dangerous behavior. Additionally, SPS combines video-based action analysis to learn distinctive features of dangerous behaviors, optimizing the selection of pairs for comparison. The experimental results on real data demonstrate that SPS outperforms other pairwise sampling baseline models, showing its attractive practicability.

Original languageEnglish
Title of host publicationTechnologies and Applications of Artificial Intelligence - 28th International Conference, TAAI 2023, Proceedings
EditorsChao-Yang Lee, Chun-Li Lin, Hsuan-Ting Chang
PublisherSpringer Science and Business Media Deutschland GmbH
Pages46-60
Number of pages15
ISBN (Print)9789819717101
DOIs
Publication statusPublished - 2024
Event28th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2023 - Yunlin, Taiwan
Duration: 2023 Dec 12023 Dec 2

Publication series

NameCommunications in Computer and Information Science
Volume2074 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference28th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2023
Country/TerritoryTaiwan
CityYunlin
Period23-12-0123-12-02

All Science Journal Classification (ASJC) codes

  • General Computer Science
  • General Mathematics

Fingerprint

Dive into the research topics of 'Strategic Pairwise Selection for Labeling High-Risk Action from Video-Based Data'. Together they form a unique fingerprint.

Cite this