Stacked Denoising Tensor Auto-Encoder for Action Recognition With Spatiotemporal Corruptions
Spatially or temporally corrupted action videos are impractical for recognition via vision or learning models. It usually happens when streaming data are captured from unintended moving cameras, which bring occlusion or camera vibration and accordingly result in arbitrary loss of spatiotemporal info...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 27(2018), 4 vom: 20. Apr., Seite 1878-1887
|
|---|
| 1. Verfasser: |
Jia, Chengcheng
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Shao, Ming,
Li, Sheng,
Zhao, Handong,
Fu, Yun |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2018
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|
|---|
| Schlagworte: | Journal Article |
|---|