Spatial Propagation Network

Spatial Propagation Networks (SPNs) are a class of neural networks designed to leverage spatial relationships within data for tasks like change detection, anomaly detection, and depth completion. Current research focuses on improving SPN architectures through techniques such as incorporating temporal information (creating spatiotemporal SPNs), employing attention mechanisms for adaptive feature weighting, and utilizing graph convolutional networks to model complex geometric relationships. These advancements enhance the accuracy and efficiency of SPNs across diverse applications, including remote sensing, video surveillance, and autonomous driving, by enabling more robust and context-aware data processing.

Papers

November 17, 2024

STOP: Spatiotemporal Orthogonal Propagation for Weight-Threshold-Leakage Synergistic Training of Deep Spiking Neural Networks
Haoran Gao, Xichuan Zhou, Yingcheng Lin, Min Tian, Liyuan Liu, Cong Shi
Sparse Activation Deep Spiking Neural Network Synergy Oriented LeARning Spatial Propagation Network

June 9, 2024

SRC-Net: Bi-Temporal Spatial Relationship Concerned Network for Change Detection
Hongjia Chen, Xin Xu, Fangling Pu
Spatio Temporal Change Detection Bi Temporal Image Spatial Propagation Network Spatio Temporal Relationship

June 17, 2023

Multi-scale Spatial-temporal Interaction Network for Video Anomaly Detection
Zhiyuan Ning, Zhangxun Li, Zhengliang Guo, Zile Wang, Liang Song
Video Anomaly Detection Spatial Network Spatial Propagation Network

May 12, 2023

Configurable Spatial-Temporal Hierarchical Analysis for Flexible Video Anomaly Detection
Kai Cheng, Xinhua Zeng, Yang Liu, Tian Wang, Chengxin Pang, Jing Teng, Zhaoyang Xia, Jing Liu
Video Anomaly Detection Video Anomaly Spatial Propagation Network

October 19, 2022

GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs
Xin Liu, Xiaofei Shao, Bo Wang, Yali Li, Shengjin Wang
Depth Completion Dense Depth Map Sparse Depth Spatial Propagation Network GCN Architecture

October 11, 2022

STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural Networks
Chengting Yu, Zheming Gu, Da Li, Gaoang Wang, Aili Wang, Erping Li
Neural Network Spiking Neural Network Human Attention Spatio Temporal Neuromorphic Computing Neuromorphic Datasets Temporal Convolution Temporal Receptive Field Spatial Propagation Network

July 14, 2022

Spatiotemporal Propagation Learning for Network-Wide Flight Delay Prediction
Yuankai Wu, Hongyu Yang, Yi Lin, Hong Liu
Delay Prediction Flight Delay Spatial Propagation Network Propagation Delay

May 29, 2022

Dynamic Graph Learning Based on Hierarchical Memory for Origin-Destination Demand Prediction
Ruixing Zhang, Liangzhe Han, Boyi Liu, Jiayuan Zeng, Leilei Sun
Traffic Forecasting Dynamic Graph Learning Dynamic Graph Representation Learning Hierarchical Memory Origin Destination Spatial Propagation Network Deep Spatiotemporal

May 26, 2022

Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations
Ivan Marisca, Andrea Cini, Cesare Alippi
LeArning Abstract Multivariate Time Series Autoregressive Model Spatiotemporal Graph Missing Data Imputation Spatial Propagation Network Autoregressive Graph

February 20, 2022

Dynamic Spatial Propagation Network for Depth Completion
Yuankai Lin, Tao Cheng, Qi Zhong, Wending Zhou, Hua Yang
Depth Completion Dense Depth Map New York University Depth V2 Spatial Propagation Network

Spatial Propagation Network

Papers

STOP: Spatiotemporal Orthogonal Propagation for Weight-Threshold-Leakage Synergistic Training of Deep Spiking Neural Networks

SRC-Net: Bi-Temporal Spatial Relationship Concerned Network for Change Detection

Multi-scale Spatial-temporal Interaction Network for Video Anomaly Detection

Configurable Spatial-Temporal Hierarchical Analysis for Flexible Video Anomaly Detection

GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs

STSC-SNN: Spatio-Temporal Synaptic Connection with Temporal Convolution and Attention for Spiking Neural Networks

Spatiotemporal Propagation Learning for Network-Wide Flight Delay Prediction

Dynamic Graph Learning Based on Hierarchical Memory for Origin-Destination Demand Prediction

Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations

Dynamic Spatial Propagation Network for Depth Completion