Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs

TL;DR

Skating-Mixer is a novel multimodal MLP-based architecture designed to analyze long-term figure skating videos by effectively modeling audio-visual relationships and capturing rapid movements, achieving state-of-the-art results.

Contribution

The paper introduces Skating-Mixer, a new MLP-based model with a memory recurrent unit for long-term audio-visual modeling in figure skating, along with a large, diverse FS1000 dataset.

Findings

Achieves state-of-the-art performance on Fis-V and FS1000 datasets.

Effectively models rapid movements and long-term dependencies.

Proves applicability in Olympic competition analysis.

Abstract

Figure skating scoring is challenging because it requires judging the technical moves of the players as well as their coordination with the background music. Most learning-based methods cannot solve it well for two reasons: 1) each move in figure skating changes quickly, hence simply applying traditional frame sampling will lose a lot of valuable information, especially in 3 to 5 minutes long videos; 2) prior methods rarely considered the critical audio-visual relationship in their models. Due to these reasons, we introduce a novel architecture, named Skating-Mixer. It extends the MLP framework into a multimodal fashion and effectively learns long-term representations through our designed memory recurrent unit (MRU). Aside from the model, we collected a high-quality audio-visual FS1000 dataset, which contains over 1000 videos on 8 types of programs with 7 different rating metrics, overtaking other datasets in both quantity and diversity. Experiments show the proposed method achieves SOTAs over all major metrics on the public Fis-V and our FS1000 dataset. In addition, we include an analysis applying our method to the recent competitions in Beijing 2022 Winter Olympic Games, proving our method has strong applicability.