← authors · overview

• OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
  2022 · 258 citations
• Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation
  2023 · 73 citations
• Single Stage Virtual Try-on via Deformable Attention Flows
  2022 · 72 citations
• Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese
  2022 · 55 citations
• M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers
  2021 · 8 citations
• Video Frame Interpolation with Densely Queried Bilateral Correlation
  2023 · 7 citations
• M6-Fashion: High-Fidelity Multi-modal Image Generation and Editing
  2022 · 3 citations
• CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation
  2021
• In-N-Out Generative Learning for Dense Unsupervised Video Segmentation
  2022