Conditional 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 AnsweringPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Speech Enhancement | 7 | 21.21% |
Decision Making | 2 | 6.06% |
Image Enhancement | 2 | 6.06% |
Low-Light Image Enhancement | 2 | 6.06% |
Question Answering | 2 | 6.06% |
Relation Network | 2 | 6.06% |
Video Question Answering | 2 | 6.06% |
3D Multi-Object Tracking | 1 | 3.03% |
3D Object Detection | 1 | 3.03% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |