Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
relational_reasoning [2018/06/22 23:39]
admin
relational_reasoning [2018/08/02 02:20] (current)
admin
Line 15: Line 15:
 we propose a hierarchical particle-based object representation that covers a wide variety of types of three-dimensional objects, including both arbitrary rigid geometrical shapes and deformable materials. We then describe the Hierarchical Relation Network (HRN), an end-to-end differentiable neural network based on hierarchical graph convolution,​ that learns to predict physical dynamics in this representation. ​ we propose a hierarchical particle-based object representation that covers a wide variety of types of three-dimensional objects, including both arbitrary rigid geometrical shapes and deformable materials. We then describe the Hierarchical Relation Network (HRN), an end-to-end differentiable neural network based on hierarchical graph convolution,​ that learns to predict physical dynamics in this representation. ​
  
 +https://​arxiv.org/​abs/​1807.10982v1 Actor-Centric Relation Network
 +
 +Our approach is weakly supervised and mines the relevant elements automatically with an actor-centric relational network (ACRN). ACRN computes and accumulates pair-wise relation information from actor and global scene features, and generates relation features for action classification. It is implemented as neural networks and can be trained jointly with an existing action detection system.