FineSkiing: A Fine-grained Benchmark for Skiing Action Quality Assessment

TL;DR

FineSkiing introduces a detailed skiing action quality dataset with sub-score annotations and a novel scoring method that mimics professional referees, improving accuracy and interpretability in sports action evaluation.

Contribution

The paper presents the first fine-grained skiing AQA dataset with sub-score annotations and a new scoring approach that enhances reliability by modeling referee judgment processes.

Findings

Achieved state-of-the-art performance on the new dataset.

Enhanced scoring accuracy through stage-aware segmentation and fusion.

Improved robustness to camera viewpoint changes.

Abstract

Action Quality Assessment (AQA) aims to evaluate and score sports actions, which has attracted widespread interest in recent years. Existing AQA methods primarily predict scores based on features extracted from the entire video, resulting in limited interpretability and reliability. Meanwhile, existing AQA datasets also lack fine-grained annotations for action scores, especially for deduction items and sub-score annotations. In this paper, we construct the first AQA dataset containing fine-grained sub-score and deduction annotations for aerial skiing, which will be released as a new benchmark. For the technical challenges, we propose a novel AQA method, named JudgeMind, which significantly enhances performance and reliability by simulating the judgment and scoring mindset of professional referees. Our method segments the input action video into different stages and scores each stage to enhance accuracy. Then, we propose a stage-aware feature enhancement and fusion module to boost the perception of stage-specific key regions and enhance the robustness to visual changes caused by frequent camera viewpoints switching. In addition, we propose a knowledge-based grade-aware decoder to incorporate possible deduction items as prior knowledge to predict more accurate and reliable scores. Experimental results demonstrate that our method achieves state-of-the-art performance.