JIST: Joint Image and Sequence Training for Sequential Visual Place Recognition.
Gabriele Moreno BertonGabriele TrivignoBarbara CaputoCarlo MasonePublished in: IEEE Robotics Autom. Lett. (2024)
Keyphrases
- input image
- single image
- image data
- low level
- image content
- image classification
- image analysis
- image retrieval
- multiscale
- human visual
- template matching
- image segmentation
- region of interest
- visually similar
- image features
- visual appearance
- visual perception
- visual cues
- spatial layout
- image regions
- image matching
- computer vision
- keypoints
- segmentation method
- image representation
- visual information
- vector field
- spatial information
- pixel values
- human observers
- high resolution
- optical flow
- medical image retrieval