Attention-Enhanced Cross-modal Localization Between 360 Images and Point Clouds.
Zhipeng ZhaoHuai YuChenwei LyvWen YangSebastian A. SchererPublished in: CoRR (2022)
Keyphrases
- point cloud
- cross modal
- image retrieval
- image database
- image data
- perceptual information
- visual similarity
- laser scanner
- three dimensional
- image classification
- input image
- multi modal
- image matching
- image features
- object recognition
- object localization
- image content
- image annotation
- visual data
- machine learning
- face recognition
- viewpoint
- multimedia retrieval
- content based retrieval
- spatial relationships
- image collections
- image understanding
- feature vectors
- feature points