scholarly journals Modelling of Trends in Twitter Using Retweet Graph Dynamics

2014 ◽  
pp. 132-147 ◽  
Author(s):  
Marijn ten Thij ◽  
Tanneke Ouboter ◽  
Daniël Worm ◽  
Nelly Litvak ◽  
Hans van den Berg ◽  
...  
Keyword(s):  
Graph Dynamics

The Distinctions Between State, Parameter and Graph Dynamics in Sensorimotor Control and Coordination

2006 ◽  
pp. 63-73 ◽  
Author(s):  
Elliot Saltzman ◽  
Hosung Nam ◽  
Louis Goldstein ◽  
Dani Byrd
Keyword(s):  
State Parameter ◽  
Sensorimotor Control ◽  
Graph Dynamics

scholarly journals Learning Graph Dynamics using Deep Neural Networks

2018 ◽  
Vol 51 (2) ◽  
pp. 433-438 ◽  
Author(s):  
Apurva Narayan ◽  
Peter H. O’N Roe
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Graph Dynamics

scholarly journals Causal graph dynamics

2013 ◽  
Vol 223 ◽  
pp. 78-93 ◽  
Author(s):  
Pablo Arrighi ◽  
Gilles Dowek
Keyword(s):  
Causal Graph ◽  
Graph Dynamics

scholarly journals Multi-Level Graph Encoding with Structural-Collaborative Relation Learning for Skeleton-Based Person Re-Identification

2021 ◽  
Author(s):  
Haocong Rao ◽  
Shihao Xu ◽  
Xiping Hu ◽  
Jun Cheng ◽  
Bin Hu
Keyword(s):  
Superior Performance ◽  
Skeleton Graph ◽  
Graph Dynamics ◽  
Connected Body ◽  
Body Component ◽  
Multi Level ◽  
Highly Correlated ◽  
High Level ◽  
Body Joints ◽  
Relation Learning

Skeleton-based person re-identification (Re-ID) is an emerging open topic providing great value for safety-critical applications. Existing methods typically extract hand-crafted features or model skeleton dynamics from the trajectory of body joints, while they rarely explore valuable relation information contained in body structure or motion. To fully explore body relations, we construct graphs to model human skeletons from different levels, and for the first time propose a Multi-level Graph encoding approach with Structural-Collaborative Relation learning (MG-SCR) to encode discriminative graph features for person Re-ID. Specifically, considering that structurally-connected body components are highly correlated in a skeleton, we first propose a multi-head structural relation layer to learn different relations of neighbor body-component nodes in graphs, which helps aggregate key correlative features for effective node representations. Second, inspired by the fact that body-component collaboration in walking usually carries recognizable patterns, we propose a cross-level collaborative relation layer to infer collaboration between different level components, so as to capture more discriminative skeleton graph features. Finally, to enhance graph dynamics encoding, we propose a novel self-supervised sparse sequential prediction task for model pre-training, which facilitates encoding high-level graph semantics for person Re-ID. MG-SCR outperforms state-of-the-art skeleton-based methods, and it achieves superior performance to many multi-modal methods that utilize extra RGB or depth features. Our codes are available at https://github.com/Kali-Hac/MG-SCR.

Dynamic Approach to Analysis of Structures Described by Graphs (Foundations of Graph-Dynamics)

1987 ◽  
pp. 69-136 ◽  
Author(s):  
M. A. Aizerman ◽  
L. A. Gusev ◽  
S. V. Petrov ◽  
I. M. Smirnova ◽  
L. A. Tenenbaum
Keyword(s):  
Dynamic Approach ◽  
Graph Dynamics

Random Graph Dynamics by Rick Durrett

2007 ◽  
Vol 75 (3) ◽  
pp. 428-428
Author(s):  
Ole E. Barndorff-Nielsen
Keyword(s):  
Random Graph ◽  
Graph Dynamics
Sign in / Sign up

Export Citation Format

Share Document