SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis

Documenti analoghi

• EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation
  di: Zhang, Xiangyue, et al.
  Pubblicazione: (2025)
• Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints
  di: Zhang, Xiangyue, et al.
  Pubblicazione: (2025)
• Generative Motion Stylization of Cross-structure Characters within Canonical Motion Space
  di: Zhang, Jiaxu, et al.
  Pubblicazione: (2024)
• Not All Frames Are Equal: Complexity-Aware Masked Motion Generation via Motion Spectral Descriptors
  di: Zhou, Pengfei, et al.
  Pubblicazione: (2026)
• Make-A-Character 2: Animatable 3D Character Generation From a Single Image
  di: Liu, Lin, et al.
  Pubblicazione: (2025)