Sorry, you need to enable JavaScript to visit this website.

S3D: Stacking Segmental P3D for Action Quality Assessment

Citation Author(s):
Ye Tian, Austin Reiter, Gregory D. Hager, Trac D. Tran
Submitted by:
Xiang Xiang
Last updated:
5 October 2018 - 2:08am
Document Type:
Presentation Slides
Document Year:
2018
Event:
Presenters:
Xiang Xiang; Trac D. Tran
Paper Code:
WQ.L1.4
 

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.

up
1 user has voted: Xiang Xiang

Comments

There're business cases to automatically suggest scores for Winter Olympic skating videos and Summer Olympic diving videos.