Unsupervised Person Re-Identification via Multi-Order Cross-View Graph Adversarial Network
Unsupervised person re-identification (re-id) is an effective analysis for video surveillance in practice, which can train a pedestrian matching model without any annotations, and it is easy to deploy in unseen camera scenarios. The most challenging problem in unsupervised re-id task is the huge dis...
Na minha lista:
| Principais autores: | , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado em: |
IEEE
2021-01-01
|
| coleção: | IEEE Access |
| Assuntos: | |
| Acesso em linha: | https://ieeexplore.ieee.org/document/9312041/ |
| Tags: |
Sem tags, seja o primeiro a adicionar uma tag!
|