CAHIR: Co-Attentive Hierarchical Image Representations for Visual Place Recognition.
Guohao PengHeshan LiYifeng HuangJun ZhangMingxing WenSingh RahulDanwei WangPublished in: ICRA (2023)
Keyphrases
- image representation
- hierarchical structure
- image classification
- multiscale
- bag of words
- visual features
- quadtree
- object recognition
- image content
- visual words
- visual information
- sparse coding
- receptive fields
- image features
- visual vocabulary
- feature space
- scene classification
- image retrieval
- visual motion
- representation scheme
- sparse representation
- low level
- low level features
- feature representations
- image classification and retrieval
- coarse to fine
- region segmentation
- bag of features
- visual content
- visual recognition
- visual search
- scene recognition
- high level
- spatial pyramid
- visual attention
- spatial pyramid matching
- pre attentive
- unsupervised learning
- visual recognition tasks
- gaussian mixture modeling