3D Representations
3-dimensional interaction space
Introduced by Nwoye et al. in Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action TripletsA trainable 3D interaction space aims to captures the associations between the triplet components and helps model the recognition of multiple triplets in the same frame.
Source: Nwoye et al.
Image source: Nwoye et al.
Source: Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| 3D Instance Segmentation | 2 | 18.18% |
| Instance Segmentation | 2 | 18.18% |
| Semantic Segmentation | 2 | 18.18% |
| Time Series Analysis | 1 | 9.09% |
| Action Localization | 1 | 9.09% |
| Action Recognition | 1 | 9.09% |
| Action Triplet Recognition | 1 | 9.09% |
| Weakly Supervised Action Localization | 1 | 9.09% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
