Shilong Liu

object detection (6) semantic segmentation (4) instance segmentation (3) transformer architecture (3) deformable attention (3) image segmentation (3) multimodal learning (2) visual grounding (2) panoptic segmentation (2) detection transformer (2) open-vocabulary segmentation (2) agent system (2) information retrieval (1) pose estimation (1) in-context learning (1) attention mechanism (1) transfer learning (1) self-supervised learning (1) multi-view fusion (1) visual reasoning (1)