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

TL;DR

This paper introduces a deep learning-based pairwise ranking method to assess skill levels from videos across various tasks, aiming to automate the organization and evaluation of skill in video collections.

Contribution

The paper proposes a novel supervised deep ranking loss function that learns discriminative features for skill assessment from videos, applicable to multiple tasks.

Findings

Achieved 70-83% accuracy in correctly ordering skill videos

Demonstrated robustness through sensitivity analysis

Applicable across diverse tasks like surgery, drawing, and cooking

Abstract

We present 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.