# 1st Place Solution to the 1st SkatingVerse Challenge

arXiv: https://arxiv.org/abs/2404.14032 · HTML: https://mlsanity.com/paper/2404.14032/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 22 Apr 2024.

## Builds on (most cited first, 5 of 5)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)

## Abstract (arXiv)

This paper presents the winning solution for the 1st SkatingVerse Challenge. We propose a method that involves several steps. To begin, we leverage the DINO framework to extract the Region of Interest (ROI) and perform precise cropping of the raw video footage. Subsequently, we employ three distinct models, namely Unmasked Teacher, UniformerV2, and InfoGCN, to capture different aspects of the data. By ensembling the prediction results based on logits, our solution attains an impressive leaderboard score of 95.73%.