Dancing to the music

By Eduardo de Campos Valadares, C. P. Anconi. 2000

352 citations recorded by the source corpus.

Subfields: Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/6034a34aeb4bfac56a60c212d7a5c1cc5785c0e2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistical and Nonlinear Physics

1. Sen Wang
2. Tao Chen
3. Fangzhou Hong
4. Chen Change Loy
5. Bin Fu
6. Chuan Guo
7. Gang Yu
8. Wen Liu

Citations in the corpus

• Action-Conditioned 3D Human Motion Synthesis with Transformer VAE (2021, neutral): “Music-to-Dance [36] and [38] study musicconditioned generation.”
• Generating Human Motion from Textual Descriptions with Discrete Representations (2023, background): “Motion can also be generated with music to produce 3D dance motion [6,13,37,38,40,41].”
• TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts (2022, methodology): “Therefore, two stochastic methods in other related fields are adopted here for more fair and in-depth evaluations: MoCoGAN [44] and Dance2Music [24].”
• Generating Diverse and Natural 3D Human Motions from Text (2022, methodology): “Considering the stochastic nature of our task, we adapt two non-deterministic methods from re-lated fields for more fair and thorough evaluations: MoCo-GAN [38] and Dance2Music [17].”
• Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory (2022, background): “In recent years, with the emergence of deep learning, many works design a dedicated network structure, including CNNs [14], RNNs [37, 3, 40, 15], GCNs [41, 35, 9], GANs [25, 36] and Transformers [29, 30, 28], to map the given music to a joint sequence of the continuous human pose space directly.”
• MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model (2022, methodology): “Quantitative Results: We compare our proposed Motion-Diffuse with five baseline models: Language2Pose [10], Text2Gesture [80], MoCoGAN [81], Dance2Music [46], and Guo et al. [48].”
• ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model (2023, methodology): “The pose is defined as a tuple of length seven: ( r va , r vx , r vz , r h , j p , j v , j r ) , where r va ∈ R is the root angular velocity along Y-axis, and r vx , r vz ∈ R are the root linear velocities along X-axis and Z-axis respectively.”
• Executing your Commands via Motion Diffusion in Latent Space (2022, background): “Human Motion Synthesis allows rich inputs of multimodal data, such as text [16, 47, 69, 18, 2, 28], action category [46, 19], incomplete pose sequences [12, 20, 69], control signals [65, 66, 45], musics [34, 33, 32] and image(s) [55, 9], here, we focus on some typical tasks.”