Video-based person re-identification via spatio-temporal attentional and two-stream fusion convolutional networks.
Deqiang OuyangYonghui ZhangJie ShaoPublished in: Pattern Recognit. Lett. (2019)
Keyphrases
- person re identification
- spatio temporal
- sparse coding
- metric learning
- data fusion
- video surveillance
- natural images
- space time
- data streams
- social networks
- camera network
- sparse representation
- image patches
- image sequences
- feature representation
- communication networks
- image classification
- moving objects
- unsupervised learning
- network structure
- feature space
- object recognition
- image fusion
- linear combination
- generative model
- riemannian manifolds
- feature vectors