OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding.
Ke-Jyun WangYun-Hsuan LiuHung-Ting SuJen-Wei WangYu-Siang WangWinston H. HsuWen-Chin ChenPublished in: CoRR (2021)
Keyphrases
- d scene
- outdoor images
- indoor and outdoor scenes
- programming language
- video sequences
- real scenes
- single image
- image set
- language learning
- benchmark datasets
- real time
- intelligent agents
- mobile robot
- dynamic scenes
- scene understanding
- natural language
- photo collections
- observed scene
- three dimensional
- database
- robotic systems
- complex scenes
- cognitive processes
- synthetic datasets
- image transformations