Img2Loc: Revisiting Image Geolocalization using Multi-modality Foundation Models and Image-based Retrieval-Augmented Generation.
Zhongliang ZhouJielu ZhangZihan GuanMengxuan HuNi LaoLan MuSheng LiGengchen MaiPublished in: SIGIR (2024)
Keyphrases
- multi modality
- image retrieval
- input image
- single image
- image analysis
- multi modal
- multimodal images
- multiscale
- vector field
- image content
- information theoretic
- relevance feedback
- feature extraction
- feature points
- edge detection
- image registration
- high resolution
- computer vision
- decision support system
- mutual information
- energy function
- medical imaging
- feature space