Visual Grounding in Video for Unsupervised Word Translation.
Gunnar A. SigurdssonJean-Baptiste AlayracAida NematzadehLucas SmairaMateusz MalinowskiJoão CarreiraPhil BlunsomAndrew ZissermanPublished in: CVPR (2020)
Keyphrases
- visual data
- visual cues
- visual analysis
- video data
- video sequences
- video streams
- statistical machine translation
- visual information
- video search
- translation model
- video retrieval
- video content
- machine translation system
- unsupervised learning
- unsupervised manner
- english words
- video frames
- content based video retrieval
- real time
- video database
- multimedia
- syntactic categories
- pointwise mutual information
- co occurrence
- visual perception
- video clips
- multimedia data
- machine translation
- word meanings
- query translation
- video analysis
- word segmentation
- visual features
- supervised learning
- semi supervised
- low level