Jianzong Wu

Latest

• RelationBooth: Towards Relation-Aware Customized Object Generation
• Motionbooth: Motion-aware customized text-to-video generation
• Towards robust referring image segmentation
• Towards open vocabulary learning: A survey
• Towards language-driven video inpainting via multimodal large language models
• Betrayed by captions: Joint caption grounding and generation for open vocabulary instance segmentation