DeCo-DETR builds hierarchical semantic prototypes offline and uses decoupled training streams to deliver competitive zero-shot open-vocabulary detection with improved inference speed.
Pengkai Zhu, Hanxiao Wang, and Venkatesh Saligrama
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Presents an open ROS2-based end-to-end navigation system for quadruped robots achieving over 88% success in zero-shot real-world indoor navigation tasks using semantic scene graphs and LLM planning.
citing papers explorer
-
DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection
DeCo-DETR builds hierarchical semantic prototypes offline and uses decoupled training streams to deliver competitive zero-shot open-vocabulary detection with improved inference speed.
-
Open-Architecture End-to-End System for Real-World Autonomous Robot Navigation
Presents an open ROS2-based end-to-end navigation system for quadruped robots achieving over 88% success in zero-shot real-world indoor navigation tasks using semantic scene graphs and LLM planning.