ProSkill: Segment-Level Skill Assessment in Procedural Videos

TL;DR

ProSkill introduces a large-scale, action-level skill assessment benchmark dataset for procedural videos, enabling more comprehensive and objective evaluation of human skills in complex tasks.

Contribution

It presents the first dataset with absolute and pairwise skill annotations for procedural tasks, along with a scalable annotation protocol and benchmarking of current algorithms.

Findings

Current state-of-the-art algorithms perform suboptimally on ProSkill.

ProSkill enables evaluation of both ranking-based and pairwise skill assessment methods.

The dataset highlights challenges in automatic skill assessment for complex procedural videos.

Abstract

Skill assessment in procedural videos is crucial for the objective evaluation of human performance in settings such as manufacturing and procedural daily tasks. Current research on skill assessment has predominantly focused on sports and lacks large-scale datasets for complex procedural activities. Existing studies typically involve only a limited number of actions, focus on either pairwise assessments (e.g., A is better than B) or on binary labels (e.g., good execution vs needs improvement). In response to these shortcomings, we introduce ProSkill, the first benchmark dataset for action-level skill assessment in procedural tasks. ProSkill provides absolute skill assessment annotations, along with pairwise ones. This is enabled by a novel and scalable annotation protocol that allows for the creation of an absolute skill assessment ranking starting from pairwise assessments. This protocol leverages a Swiss Tournament scheme for efficient pairwise comparisons, which are then aggregated into consistent, continuous global scores using an ELO-based rating system. We use our dataset to benchmark the main state-of-the-art skill assessment algorithms, including both ranking-based and pairwise paradigms. The suboptimal results achieved by the current state-of-the-art highlight the challenges and thus the value of ProSkill in the context of skill assessment for procedural videos. All data and code are available at https://fpv-iplab.github.io/ProSkill/