Multimodal Representation Learning With Text and Images.
Aishwarya JayagopalAnkireddy Monica AiswaryaAnkita GargSrinivasan Kolumam NandakumarPublished in: CoRR (2022)
Keyphrases
- input image
- learning algorithm
- ground truth
- test images
- image data
- image features
- perceptual information
- three dimensional
- learning process
- multi modal
- feature representation
- edge detection
- information retrieval
- complex background
- image collections
- active learning
- image analysis
- reinforcement learning
- supervised learning
- information extraction
- feature vectors
- textual descriptions
- machine learning