Who's Better? Who's Best? Pairwise Deep Ranking for Skill Determination

This paper presents a method for assessing skill from video, applicable to a variety of tasks, ranging from surgery to drawing and rolling pizza dough. We formulate the problem as pairwise (who's better?) and overall (who's best?) ranking of video collections, using supervised deep ranking...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition S. 6057 - 6066
Hauptverfasser: Doughty, Hazel, Damen, Dima, Mayol-Cuevas, Walterio
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2018
Schlagworte:
Distance measurement
Neural networks
Sports
Surgery
Task analysis
Training
Video sequences
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper presents a method for assessing skill from video, applicable to a variety of tasks, ranging from surgery to drawing and rolling pizza dough. We formulate the problem as pairwise (who's better?) and overall (who's best?) ranking of video collections, using supervised deep ranking. We propose a novel loss function that learns discriminative features when a pair of videos exhibit variance in skill, and learns shared features when a pair of videos exhibit comparable skill levels. Results demonstrate our method is applicable across tasks, with the percentage of correctly ordered pairs of videos ranging from 70% to 83% for four datasets. We demonstrate the robustness of our approach via sensitivity analysis of its parameters. We see this work as effort toward the automated organization of how-to video collections and overall, generic skill determination in video.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00634