Login / Signup
CSPFormer: A cross-spatial pyramid transformer for visual place recognition.
Zhenyu Li
Pengjie Xu
Published in:
Neurocomputing (2024)
Keyphrases
</>
spatial pyramid
image classification
visual vocabulary
scene recognition
visual features
visual information
image representation
object class
visual words
object classification
class specific
image retrieval
face recognition
bag of features
image collections
scene classification
low level
feature extraction