Superpixel Group Mining for Manipulation Action Recognition

Tianjun Huang, Stephen McKenna

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

18 Downloads (Pure)


Manipulation action recognition is a challenging problem in computer vision. We previously reported a system based on matching groups of superpixels. In this paper, we modify the superpixel group mining algorithm and report results on two datasets. Recognition accuracies are comparable with those reported using deep learning. The representation used in our approach is amenable to interpretation. Specifically, visualisation of matched groups provides a level of explanation for recognition decisions and insights into the likely generalisation ability of action representations.
Original languageEnglish
Title of host publicationReaLX 2018
Subtitle of host publicationProceedings of the SICSA Workshop on Reasoning, Learning and Explainability
EditorsKyle Martin , Nirmalie Wiratunga, Leslie S. Smith
Number of pages5
Publication statusPublished - 27 Jul 2018

Publication series

NameCEUR Workshop Proceedings
ISSN (Electronic)1613-0073


  • Action recognition
  • Computer vision
  • Superpixel group mining

Fingerprint Dive into the research topics of 'Superpixel Group Mining for Manipulation Action Recognition'. Together they form a unique fingerprint.

  • Student Theses

    Sequential Recognition of Manipulation Actions Using Superpixel Group Mining

    Author: Huang, T., 2019

    Supervisor: McKenna, S. (Supervisor) & Zhang, J. (Supervisor)

    Student thesis: Doctoral ThesisDoctor of Philosophy


    Cite this

    Huang, T., & McKenna, S. (2018). Superpixel Group Mining for Manipulation Action Recognition. In K. Martin , N. Wiratunga, & L. S. Smith (Eds.), ReaLX 2018: Proceedings of the SICSA Workshop on Reasoning, Learning and Explainability (Vol. 2151, pp. 1-5). (CEUR Workshop Proceedings). CEUR-WS.