Learned Visual Features to Textual Explanations.
Saeid Asgari TaghanakiAliasghar KhaniAmir KhasahmadiAditya SanghiKarl D. D. WillisAli Mahdavi-AmiriPublished in: CoRR (2023)
Keyphrases
- visual features
- visual content
- keywords
- visual information
- textual features
- image classification
- image retrieval
- low level features
- low level
- image search
- textual information
- visual and textual features
- image annotation
- semantic gap
- bag of features
- image collections
- visual appearance
- visual data
- semantic concepts
- semantic features
- global features
- textual and visual features
- multimedia
- probabilistic latent semantic analysis
- metadata
- key frames
- bridge the semantic gap
- low level visual features
- visual similarity
- similarity measure
- video shots
- machine learning
- feature extraction
- motion features
- audio features
- visual descriptors
- object recognition
- multi modal