Depth-Aware Vision-and-Language Navigation using Scene Query Attention Network.
Sinan TanMengmeng GeDi GuoHuaping LiuFuchun SunPublished in: ICRA (2022)
Keyphrases
- communication cost
- database
- d scene
- data structure
- query processing
- real time
- image sequences
- query evaluation
- response time
- depth map
- rewriting rules
- user queries
- algebraic operations
- single image
- computer vision
- defocused images
- wireless sensor networks
- network structure
- visual attention
- depth estimation
- scene understanding
- three dimensional
- video sequences
- relevance feedback
- query expansion
- input image
- peer to peer
- visual query language
- unstructured peer to peer
- depth images
- multiple objects
- dynamic scenes
- data sources
- vision system