Jianwen Jiang

12

Papers

108

Total Citations

Papers (12)

OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models

CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body Generation

FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation

Self-Supervised Motion Learning From Static Images

NGC: A Unified Framework for Learning With Open-World Noisy Data

ViM: Vision Middleware for Unified Downstream Transferring

RLIPv2: Fast Scaling of Relational Language-Image Pre-Training

VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal Retrieval

MobilePortrait: Real-Time One-Shot Neural Head Avatars on Mobile Devices

Structured Model Probing: Empowering Efficient Transfer Learning by Structured Regularization

Grow and Merge: A Unified Framework for Continuous Categories Discovery

RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection