Scholarlink

<p>Synthesis of dance from music is a very challenging task of media transformation because the characteristics of swift and sequential movement of major parts of the body in a video are required to be preserved using a small set of audio and motion data. This paper proposes a novel architecture to learn dance of different styles including Ballet, Rumba, Cha-Cha, Tango and Waltz from musical videos. In particular, a deep learning architecture comprising celebrated convolutional neural network, long short-term memory network, and a novel probabilistic learning model, named, the mixture density network that well preserved the spatiotemporal coherence are used to generate rhythmic movements of stick diagram from music. Then a suitable generative adversarial network with innovative post-processing technique is integrated to synthesize realistic dance from the rhythmic movements of the stick diagram. Experiments have been carried out on YouTube and Motion Capture datasets to evaluate the performance of the proposed learning model. The results reveal that the proposed algorithm outperforms the existing ones in terms of commonly-used performance indices. The proposed model demonstrates robustness across music genres, with failure cases occurring primarily under ill-posed conditions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Synthesis of style-specific dance by learning body gestures from music

  • 期刊论文

  • 发表日期：

    2025年9月4日

查看全文
  • Md Shazid Islam,
  • S. M. Mahbubur Rahman

摘要

Synthesis of dance from music is a very challenging task of media transformation because the characteristics of swift and sequential movement of major parts of the body in a video are required to be preserved using a small set of audio and motion data. This paper proposes a novel architecture to learn dance of different styles including Ballet, Rumba, Cha-Cha, Tango and Waltz from musical videos. In particular, a deep learning architecture comprising celebrated convolutional neural network, long short-term memory network, and a novel probabilistic learning model, named, the mixture density network that well preserved the spatiotemporal coherence are used to generate rhythmic movements of stick diagram from music. Then a suitable generative adversarial network with innovative post-processing technique is integrated to synthesize realistic dance from the rhythmic movements of the stick diagram. Experiments have been carried out on YouTube and Motion Capture datasets to evaluate the performance of the proposed learning model. The results reveal that the proposed algorithm outperforms the existing ones in terms of commonly-used performance indices. The proposed model demonstrates robustness across music genres, with failure cases occurring primarily under ill-posed conditions.