Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation.
Shizhe ChenPierre-Louis GuhurMakarand TapaswiCordelia SchmidIvan LaptevPublished in: CoRR (2022)
Keyphrases
- computer vision
- graph representation
- global scale
- graph theory
- graph structure
- natural language
- image processing
- programming language
- vision system
- scale space
- random walk
- global consistency
- graph theoretic
- graph matching
- undirected graph
- graph model
- global information
- directed graph
- global structure
- real time
- neural network
- target language
- specification language
- graph based algorithm
- rewriting rules
- robot navigation
- graph partitioning
- small scale
- bipartite graph
- power system
- natural language processing
- fuzzy logic
- image segmentation
- artificial intelligence