Tianheng Cheng

object detection (4) semantic segmentation (3) vision-language model (3) instance segmentation (2) image segmentation (1) vision transformer (1) reinforcement learning (1) pseudo labeling (1) self-supervised learning (1) knowledge mining (1) weakly supervised learning (1) knowledge distillation (1) chain-of-thought reasoning (1) point cloud (1) referring expression (1) vision-based perception (1) depth estimation (1) visual grounding (1) scene understanding (1) zero-shot learning (1)