Jiangning Zhang

Latest

• Decouple and track: Benchmarking and improving video diffusion transformers for motion transfer
• Motionbooth: Motion-aware customized text-to-video generation
• Explore In-Context Segmentation via Latent Diffusion Models
• Sfnet: Faster and accurate semantic segmentation via semantic flow
• Towards open vocabulary learning: A survey
• Towards language-driven video inpainting via multimodal large language models