InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions.
CoRR, June, 2025
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models.
CoRR, February, 2025
CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body Generation.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation.
CoRR, 2024
CyberHost: Taming Audio-driven Avatar Diffusion Model with Region Codebook Attention.
CoRR, 2024
MobilePortrait: Real-Time One-Shot Neural Head Avatars on Mobile Devices.
CoRR, 2024
Superior and Pragmatic Talking Face Generation with Teacher-Student Framework.
CoRR, 2024
HandMIM: Pose-Aware Self-Supervised Learning for 3D Hand Mesh Estimation.
CoRR, 2023
Person Re-Identification by Context-Aware Part Attention and Multi-Head Collaborative Learning.
IEEE Trans. Inf. Forensics Secur., 2022
Deep Learning for Person Re-Identification: A Survey and Outlook.
IEEE Trans. Pattern Anal. Mach. Intell., 2022
Video person re-identification with global statistic pooling and self-attention distillation.
Neurocomputing, 2021