S3D: Stacking Segmental P3D for Action Quality Assessment

Xiang Xiang, Ye Tian, Austin Reiter, Gregory D. Hager, Trac D. Tran

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

Abstract

Action quality assessment is crucial in areas of sports, surgery and assembly line where action skills can be evaluated. In this paper, we propose the Segment-based P3D-fused network S3D built-upon ED-TCN and push the performance on the UNLV-Dive dataset by a significant margin. We verify that segment-aware training performs better than full-video training which turns out to focus on the water spray. We show that temporal segmentation can be embedded with few efforts.

Original languageEnglish (US)
Title of host publication2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
PublisherIEEE Computer Society
Pages928-932
Number of pages5
ISBN (Electronic)9781479970612
DOIs
StatePublished - Aug 29 2018
Event25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece
Duration: Oct 7 2018Oct 10 2018

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference25th IEEE International Conference on Image Processing, ICIP 2018
CountryGreece
CityAthens
Period10/7/1810/10/18

Keywords

  • 3D CNN
  • Action quality
  • Regression
  • Spatiotemporal
  • Temporal convolution
  • Temporal segmentation

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint Dive into the research topics of 'S3D: Stacking Segmental P3D for Action Quality Assessment'. Together they form a unique fingerprint.

Cite this