Yangyang Cai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yangyang Cai has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Miao Cheng
Research Institute of Electrical Communication, Tohoku University, Sendai, Japan
2 shared publications - Yoshifumi Kitamura
Research Institute of Electrical Communication, Tohoku University, Sendai, Japan
2 shared publications - Chia-Huei Tseng
Research Institute of Electrical Communication, Tohoku University, Sendai, Japan
1 shared publication - Ken Fujiwara
Department of Psychology, National Chung Cheng University, Minxiong, Taiwan
1 shared publication - Lin Gu
Beijing National Center for Electron Microscopy and Laboratory of Advanced Materials, School of Materials Science and Engineering, Tsinghua University, Beijing 100084, China
1 shared publication - Mingyi Shi
The University of Hong Kong
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-13
DynaConTalk: Wavelet-Constrained Diffusion for Long-Form and Controllable Holistic Co-Speech 3D Motion
Holistic co-speech animation is prone to averaging in both motion representation and speech conditioning. In coordinate-space diffusion, slow body posture, mid-frequency gesture strokes, and fast hand or facial details are entangled in one prediction target, often producing low-variance, over-smoothed motion. Meanwhile, fixed multimodal conditioning can let dense rhythmic and acoustic cues dominate sparse semantic cues, weakening rare content-specific gestures. We present DynaConTalk, a wavelet-constrained diffusion framework for long-form and controllable holistic co-speech motion generation. DynaConTalk performs diffusion in stationary wavelet transform (SWT) coefficient space, where temporally aligned bands separate coarse posture evolution, gesture strokes, and high-frequency expressive details. We further introduce dynamic proposal-consensus conditioning to adaptively balance rhythmic, acoustic, semantic, textual, and identity/activity cues according to the current speech context and denoising state. Finally, to ensure smooth transitions between windows and support flexible user control, we re-noise any reference signal - whether a keypose, a motion clip, or a short boundary condition - to match the current diffusion timestep before injecting it into the denoiser. This unified strategy allows seamless long-form generation, localized editing, and style-driven guidance to be handled within a single coherent process, without task-specific modules or post-hoc stitching. Experiments show that DynaConTalk improves gesture realism, facial accuracy, temporal continuity, and controllable editing over prior holistic co-speech generation methods. Code and data for this paper are at https://zhuyifeiabcd1.github.io/DynaConTalk/.
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-13
Open AccessDynaConTalk: Wavelet-Constrained Diffusion for Long-Form and Controllable Holistic Co-Speech 3D Motion
Holistic co-speech animation is prone to averaging in both motion representation and speech conditioning. In coordinate-space diffusion, slow body posture, mid-frequency gesture strokes, and fast hand or facial details are entangled in one prediction target, often producing low-variance, over-smoothed motion. Meanwhile, fixed multimodal conditioning can let dense rhythmic and acoustic cues dominate sparse semantic cues, weakening rare content-specific gestures. We present DynaConTalk, a wavelet-constrained diffusion framework for long-form and controllable holistic co-speech motion generation. DynaConTalk performs diffusion in stationary wavelet transform (SWT) coefficient space, where temporally aligned bands separate coarse posture evolution, gesture strokes, and high-frequency expressive details. We further introduce dynamic proposal-consensus conditioning to adaptively balance rhythmic, acoustic, semantic, textual, and identity/activity cues according to the current speech context and denoising state. Finally, to ensure smooth transitions between windows and support flexible user control, we re-noise any reference signal - whether a keypose, a motion clip, or a short boundary condition - to match the current diffusion timestep before injecting it into the denoiser. This unified strategy allows seamless long-form generation, localized editing, and style-driven guidance to be handled within a single coherent process, without task-specific modules or post-hoc stitching. Experiments show that DynaConTalk improves gesture realism, facial accuracy, temporal continuity, and controllable editing over prior holistic co-speech generation methods. Code and data for this paper are at https://zhuyifeiabcd1.github.io/DynaConTalk/.
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Culture Matters in Humanness Recognition for Human Body Motion
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessCulture Matters in Humanness Recognition for Human Body Motion