Local imperceptible adversarial attacks against human pose estimation networks
Abstract Deep neural networks are vulnerable to attacks from adversarial inputs. Corresponding attack research on human pose estimation (HPE), particularly for body joint detection, has been largely unexplored. Transferring classification-based attack methods to body joint regression tasks is not st...
I tiakina i:
| Ngā kaituhi matua: | , , , , |
|---|---|
| Hōputu: | Artigo |
| Reo: | Inglês |
| I whakaputaina: |
SpringerOpen
2023-11-01
|
| Rangatū: | Visual Computing for Industry, Biomedicine, and Art |
| Ngā marau: | |
| Urunga tuihono: | https://doi.org/10.1186/s42492-023-00148-1 |
| Ngā Tūtohu: |
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!
|