用ConvLSTM提升舞力全开自动编舞准确率
Dance Dance ConvLSTM
- 基于ConvLSTM构建新模型，改进旧版CNN-LSTM方法
- 相比前作显著提升编舞生成准确率
- 适合游戏自动化、音乐舞蹈生成研究者
《舞力全开》是一款节奏类游戏，包含歌曲和对应的舞蹈动作谱，称为谱面。玩家需在跳舞垫上按节奏踩踏对应方向。2017年，舞力全开卷积（DDC）提出一种基于CNN-LSTM架构的自动生成谱面算法。本文提出舞力全开ConvLSTM（DDCL），采用基于ConvLSTM的模型，改进原有方法，显著提升谱面生成的准确性。
原文摘要 · Abstract (English)
\textit{Dance Dance Revolution} is a rhythm game consisting of songs and accompanying choreography, referred to as charts. Players press arrows on a device referred to as a dance pad in time with steps determined by the song's chart. In 2017, the authors of Dance Dance Convolution (DDC) developed an algorithm for the automatic generation of \textit{Dance Dance Revolution} charts, utilizing a CNN-LSTM architecture. We introduce Dance Dance ConvLSTM (DDCL), a new method for the automatic generation of DDR charts using a ConvLSTM based model, which improves upon the DDC methodology and substantially increases the accuracy of chart generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。