Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning Paper • 2309.01246 • Published Sep 3, 2023 • 1
IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation Paper • 2407.10937 • Published Jul 15 • 1
DisCo: Disentangled Control for Referring Human Dance Generation in Real World Paper • 2307.00040 • Published Jun 30, 2023 • 25
Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization Paper • 2010.11594 • Published Oct 22, 2020 • 1
Language-guided Human Motion Synthesis with Atomic Actions Paper • 2308.09611 • Published Aug 18, 2023 • 1
Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation Paper • 2406.06890 • Published Jun 11 • 1