Superpixel Group Mining for Manipulation Action Recognition
Year: 2018
Type: conference-paper
Abstract: 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.
Authors: Tianjun Huang, S.J. McKenna
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2902464633
