AMIGO: Sparse Multi-Modal Graph Transformer with Shared-Context Processing for Representation Learning of Giga-pixel Images.
Ramin NakhliPuria Azadi MoghadamHaoyang MiHossein FarahaniAlexander BarasC. Blake GilksAli BashashatiPublished in: CoRR (2023)
Keyphrases
- multi modal
- image annotation
- input image
- auto annotation
- high dimensional
- image analysis
- fusing multiple
- audio visual
- image classification
- image search
- multi modality
- image registration
- image representation
- context aware
- image features
- image collections
- image retrieval
- web images
- pervasive computing
- multiple modalities
- single modality