Video Model Blocks
Conditional Relation Network
Introduced by Le et al. in Hierarchical Conditional Relation Networks for Video Question AnsweringConditional Relation Network, or CRN, is a building block to construct more sophisticated structures for representation and reasoning over video. CRN takes as input an array of tensorial objects and a conditioning feature, and computes an array of encoded output objects. Model building becomes a simple exercise of replication, rearrangement and stacking of these reusable units for diverse modalities and contextual information. This design thus supports high-order relational and multi-step reasoning.
Source: Hierarchical Conditional Relation Networks for Video Question Answering
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Speech Enhancement | 4 | 22.22% |
| Question Answering | 2 | 11.11% |
| Video Question Answering | 2 | 11.11% |
| Epidemiology | 1 | 5.56% |
| whole slide images | 1 | 5.56% |
| Time Series Analysis | 1 | 5.56% |
| Action Detection | 1 | 5.56% |
| Activity Detection | 1 | 5.56% |
| Decision Making | 1 | 5.56% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
