3DRefTransformer: Fine-Grained Object Identification in Real-World Scenes Using Natural Language.
Ahmed AbdelreheemUjjwal UpadhyayIvan SkorokhodovRawan Al YahyaJun ChenMohamed ElhoseinyPublished in: WACV (2022)
Keyphrases
- fine grained
- object identification
- real world scenes
- natural language
- coarse grained
- object recognition
- complex scenes
- image matching
- real scenes
- access control
- spatial relationships
- image sequences
- natural language processing
- spatial information
- low level
- information extraction
- high level
- depth discontinuities
- machine learning