CRN

2000년 도입 · 논문 44편에서 사용

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.

출처: Hierarchical Conditional Relation Networks for Video Question Answering

소개 논문: Hierarchical Conditional Relation Networks for Video Question Answering