Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection.
Ziteng CuiYingying ZhuLin GuGuo-Jun QiXiaoxiao LiRenrui ZhangZenghui ZhangTatsuya HaradaPublished in: ECCV (9) (2022)
Keyphrases
- low quality
- object detection
- high quality
- high resolution
- signal processing
- scene understanding
- computer vision
- signal detection
- non stationary
- face detection
- high frequency
- poor quality
- pedestrian detection
- coarse to fine
- low resolution
- object categories
- object classification
- object recognition
- palmprint
- dynamic programming
- deformable part models
- frequency domain
- fingerprint images
- multiresolution