A Feature Map is Worth a Video Frame: Rethinking Convolutional Features for Visible-Infrared Person Re-identification.
Qiaolin HeZhijie ZhengHaifeng HuPublished in: ACM Trans. Multim. Comput. Commun. Appl. (2024)
Keyphrases
- infrared
- feature maps
- video frames
- person re identification
- saliency map
- feature vectors
- infrared images
- multi sensor
- feature space
- feature extraction
- kernel function
- video data
- sparse coding
- video streams
- video sequences
- image processing
- image features
- low level
- feature selection
- unsupervised learning
- object detection
- semi supervised