X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks.
Zhaowei CaiGukyeong KwonAvinash RavichandranErhan BasZhuowen TuRahul BhotikaStefano SoattoPublished in: ECCV (36) (2022)
Keyphrases
- real time
- description languages
- databases
- image processing
- pairwise
- language learning
- programming language
- layered architecture
- service robots
- network architecture
- database
- natural language interface
- software architecture
- vision system
- management system
- expert systems
- computer vision
- relational databases
- multi task
- inference engine
- specification language
- multiple tasks
- natural language
- data mining
- data sets