CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery.
Long BaiMobarakol IslamHongliang RenPublished in: CoRR (2023)
Keyphrases
- visual field
- selective attention
- visual perception
- real time
- human vision
- visual attention
- visual processing
- programming language
- natural language
- haptic feedback
- vision system
- pre attentive
- visual information
- language learning
- image guided
- biological vision
- image processing
- minimally invasive
- visual input
- visual search
- visual query language
- mobile robot
- low level
- computer vision
- receptive fields
- computer assisted
- virtual environment
- visual features
- visual scene
- operating room
- surgical training
- visual saliency
- intraoperative
- robotic systems
- query answering
- machine translation
- image retrieval