FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding

2025-04-28

AI Summary

Existing figure skating datasets predominantly target single tasks (e.g., action recognition), lack fine-grained dual-dimensional annotations—technical (e.g., jumps, spins) and artistic—and suffer from severe underdevelopment of AI research for aesthetic sports compared to ball sports. To address this gap, we introduce FSBench, the first multimodal benchmark for figure skating. It features a novel dual-dimensional annotation schema integrating technical execution and artistic expression; a dual-track evaluation framework comprising text-based question answering (FSBench-Text) and motion–language alignment (FSBench-Motion); and an open-source training set (FSAnno) with a standardized evaluation protocol. Empirical results reveal substantial deficiencies in state-of-the-art multimodal models’ artistic understanding. FSBench bridges critical data and evaluation gaps in intelligent analysis of aesthetic sports and establishes a new paradigm for deep cognitive modeling of unstructured athletic performances.

Technology Category

• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Figure skating, known as the"Art on Ice,"is among the most artistic sports, challenging to understand due to its blend of technical elements (like jumps and spins) and overall artistic expression. Existing figure skating datasets mainly focus on single tasks, such as action recognition or scoring, lacking comprehensive annotations for both technical and artistic evaluation. Current sports research is largely centered on ball games, with limited relevance to artistic sports like figure skating. To address this, we introduce FSAnno, a large-scale dataset advancing artistic sports understanding through figure skating. FSAnno includes an open-access training and test dataset, alongside a benchmark dataset, FSBench, for fair model evaluation. FSBench consists of FSBench-Text, with multiple-choice questions and explanations, and FSBench-Motion, containing multimodal data and Question and Answer (QA) pairs, supporting tasks from technical analysis to performance commentary. Initial tests on FSBench reveal significant limitations in existing models' understanding of artistic sports. We hope FSBench will become a key tool for evaluating and enhancing model comprehension of figure skating.

Problem

• Lack of comprehensive datasets for figure skating technical and artistic evaluation
• Limited research on artistic sports compared to ball games
• Existing models show poor understanding of figure skating

Innovation

• Introduces FSAnno dataset for figure skating
• Combines technical and artistic annotations
• Provides multimodal QA pairs for evaluation