A CNN-RNN Framework for Image Annotation from Visual Cues and Social Network Metadata.
Tobia TesanPasquale CosciaLamberto BallanPublished in: ICPR (2020)
Keyphrases
- image annotation
- visual cues
- metadata
- automatic image annotation
- image understanding
- image search
- multi modal
- visual features
- visual information
- low level
- multiple visual cues
- image annotation and retrieval
- relevance model
- image content
- multi label
- image retrieval
- face recognition
- ground truth
- video sequences
- feature extraction
- computer vision