AutoTag: visual domain adaptation for autonomous retail stores through multi-modal sensing.
Carlos Ruiz DominguezJoão Diogo FalcãoPei ZhangPublished in: UbiComp/ISWC Adjunct (2019)
Keyphrases
- multi modal
- domain adaptation
- cross modal
- video search
- multiple sources
- cross domain
- semi supervised
- labeled data
- single modality
- test data
- target domain
- semi supervised learning
- multi modality
- visual information
- low level
- visual features
- semantic concepts
- high dimensional
- training data
- unlabeled data
- sentiment classification
- visual data
- transfer learning
- document classification
- similarity measure
- image annotation
- machine learning
- text categorization
- multi view
- co training
- visual cues
- co occurrence
- text mining
- supervised learning
- learning process
- multimedia