Peike Li

Latest

• JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models
• Audio-Visual Segmentation by Exploring Cross-Modal Mutual Semantics
• 🍔In-N-Out Generative Learning for Dense Unsupervised Video Segmentation
• 👗M6-Fashion: High-Fidelity Multi-modal Image Generation and Editing
• SFGN: Representing the Sequence with One Super Frame
• Open-Vocabulary Panoptic Segmentation via Multi-modal Meta-knowledge Transferring
• Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplar
• Self-Correction for Human Parsing
• Consistent Structural Relation Learning for Zero-Shot Segmentation
• Meta Parsing Networks: Towards Generalized Few-shot Scene Parsing with Adaptive Metric Learning
• When Humans Meet Machines: Towards Efficient Segmentation Networks
• Dual Embedding Learning for Video Instance Segmentation
• Going Deeper into Embedding Learning for Video Object Segmentation
• Hierarchical Temporal Modeling with Mutual Distance Matching for Video Based Person Re-Identification