S3D: Stacking Segmental P3D for Action Quality Assessment

Xiang Xiang, Ye Tian, Austin Reiter, Gregory 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

Fingerprint

Sports
Surgery
Water

Keywords

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

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Xiang, X., Tian, Y., Reiter, A., Hager, G., & Tran, T. D. (2018). S3D: Stacking Segmental P3D for Action Quality Assessment. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings (pp. 928-932). [8451364] (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP.2018.8451364

S3D : Stacking Segmental P3D for Action Quality Assessment. / Xiang, Xiang; Tian, Ye; Reiter, Austin; Hager, Gregory; Tran, Trac D.

2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society, 2018. p. 928-932 8451364 (Proceedings - International Conference on Image Processing, ICIP).

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

Xiang, X, Tian, Y, Reiter, A, Hager, G & Tran, TD 2018, S3D: Stacking Segmental P3D for Action Quality Assessment. in 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings., 8451364, Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 928-932, 25th IEEE International Conference on Image Processing, ICIP 2018, Athens, Greece, 10/7/18. https://doi.org/10.1109/ICIP.2018.8451364
Xiang X, Tian Y, Reiter A, Hager G, Tran TD. S3D: Stacking Segmental P3D for Action Quality Assessment. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society. 2018. p. 928-932. 8451364. (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2018.8451364
Xiang, Xiang ; Tian, Ye ; Reiter, Austin ; Hager, Gregory ; Tran, Trac D. / S3D : Stacking Segmental P3D for Action Quality Assessment. 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society, 2018. pp. 928-932 (Proceedings - International Conference on Image Processing, ICIP).
@inproceedings{39ed3095dbc442d38126303c0dd62803,
title = "S3D: Stacking Segmental P3D for Action Quality Assessment",
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.",
keywords = "3D CNN, Action quality, Regression, Spatiotemporal, Temporal convolution, Temporal segmentation",
author = "Xiang Xiang and Ye Tian and Austin Reiter and Gregory Hager and Tran, {Trac D.}",
year = "2018",
month = "8",
day = "29",
doi = "10.1109/ICIP.2018.8451364",
language = "English (US)",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "928--932",
booktitle = "2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings",

}

TY - GEN

T1 - S3D

T2 - Stacking Segmental P3D for Action Quality Assessment

AU - Xiang, Xiang

AU - Tian, Ye

AU - Reiter, Austin

AU - Hager, Gregory

AU - Tran, Trac D.

PY - 2018/8/29

Y1 - 2018/8/29

N2 - 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.

AB - 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.

KW - 3D CNN

KW - Action quality

KW - Regression

KW - Spatiotemporal

KW - Temporal convolution

KW - Temporal segmentation

UR - http://www.scopus.com/inward/record.url?scp=85062917125&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062917125&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2018.8451364

DO - 10.1109/ICIP.2018.8451364

M3 - Conference contribution

AN - SCOPUS:85062917125

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 928

EP - 932

BT - 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings

PB - IEEE Computer Society

ER -