The SkatingVerse Workshop & Challenge: Methods and Results

TL;DR

The paper presents the SkatingVerse Workshop & Challenge, a new benchmark for human action understanding using a large-scale skating video dataset, highlighting top methods and encouraging further research in this area.

Contribution

It introduces the SkatingVerse dataset and challenge, providing a platform for advancing human action understanding research with novel methods.

Findings

Large-scale dataset with nearly 20,000 training videos

Participation from over ten global teams

Summary of top three methods in the challenge

Abstract

The SkatingVerse Workshop & Challenge aims to encourage research in developing novel and accurate methods for human action understanding. The SkatingVerse dataset used for the SkatingVerse Challenge has been publicly released. There are two subsets in the dataset, i.e., the training subset and testing subset. The training subsets consists of 19,993 RGB video sequences, and the testing subsets consists of 8,586 RGB video sequences. Around 10 participating teams from the globe competed in the SkatingVerse Challenge. In this paper, we provide a brief summary of the SkatingVerse Workshop & Challenge including brief introductions to the top three methods. The submission leaderboard will be reopened for researchers that are interested in the human action understanding challenge. The benchmark dataset and other information can be found at: https://skatingverse.github.io/.