Cross-species learning: A low-cost approach to learning human fight from animal fight

Yujun Eugene FU, Michael Xuelin HUANG, Hong Va LEONG, Grace NGAI

Research output: Chapter in Book/Report/Conference proceedingChapters

12 Citations (Scopus)

Abstract

Detecting human fight behavior from videos is important in social signal processing, especially in the context of surveillance. However, the uncommon occurrence of real human fight events generally restricts the data collection for fight detection in machine learning, and thus hampers the performance of contemporary data-driven approaches. To address this challenge, we present a novel cross-species learning method with a set of low-computational cost motion features for fight detection. It effectively circumvents the problem of limited human fight data for data-demaining approaches. Our method exploits the intrinsic commonality between human and animal fights, such as the physical acceleration of moving body parts. It also leverages an ensemble learning mechanism to adapt useful knowledge from similar source subsets across species. Our evaluation results demonstrate the effectiveness of the proposed feature representation for cross-species adaptation. We believe that cross-species learning is not only a promising solution to the data constraint issue, but it also sheds lights on the studies of other human mental and social behaviors in cross-disciplinary research. Copyright © 2018 Association for Computing Machinery.

Original languageEnglish
Title of host publicationProceedings of the 2018 ACM Multimedia Conference, MM '18
Place of PublicationUSA
PublisherAssociation for Computing Machinery
Pages320-327
ISBN (Electronic)9781450356657
DOIs
Publication statusPublished - 2018

Citation

Fu, E. Y., Huang, M. X., Leong, H. V., & Ngai, G. (2018). Cross-species learning: A low-cost approach to learning human fight from animal fight. In Proceedings of the 2018 ACM Multimedia Conference, MM '18 (pp. 320-327). Association for Computing Machinery. https://doi.org/10.1145/3240508.3240710

Keywords

  • Transfer learning
  • Domain adaptation
  • Motion analysis
  • Violence surveillance

Fingerprint

Dive into the research topics of 'Cross-species learning: A low-cost approach to learning human fight from animal fight'. Together they form a unique fingerprint.