Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval.
Andrés MaflaSounak DeyAli Furkan BitenLluís GómezDimosthenis KaratzasPublished in: CoRR (2020)
Keyphrases
- multi modal
- fine grained
- image classification and retrieval
- coarse grained
- shape classification
- image representation
- video sequences
- three dimensional
- multi modality
- input image
- access control
- shape description
- visual features
- uni modal
- data lineage
- high dimensional
- image sequences
- matching algorithm
- keywords
- feature extraction