Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training.
Hongwei XueYupan HuangBei LiuHouwen PengJianlong FuHouqiang LiJiebo LuoPublished in: CoRR (2021)
Keyphrases
- visual field
- natural language
- visual perception
- selective attention
- multi modal
- computer vision
- visual processing
- human vision
- real time
- visual information
- visual attention
- linguistic analysis
- language learning
- programming language
- vision system
- visual features
- biological vision
- word order
- medical images
- image processing
- object recognition
- pre attentive
- language understanding
- syntactic parsing
- visual stimuli
- visual languages
- training process
- low level
- training set
- machine learning
- syntactic categories
- visual query language
- stochastic context free grammars
- context free
- conceptual graphs
- visual search
- artificial neural networks