miscellaneous-6

Crime Prediction

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in crime-prediction-6

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find crime-prediction-6 models and implementations

Datasets

Foursquare

Subtasks

No subtasks available.

Most implemented papers

Crime Prediction Based On Crime Types And Using Spatial And Temporal Criminal Hotspots

Tahani Almanie, Rsha Mirza, E. Lor•Sat Aug 08 2015

An analysis study is introduced by combining the findings of Denver crimes dataset with its demographics information in order to capture the factors that might affect the safety of neighborhoods and to help agencies to predict future crimes in a specific location within a particular time.

108

Content

0

Paper Graph

San Francisco Crime Classification

Yehya Abouelnaga•Tue Jul 12 2016

This paper explores the data, and explains in details the tools used to achieve an accuracy that ranks at top %18, as of May 19th, 2016, in San Francisco Crime Classification.

6 0

Paper Graph

AIST: An Interpretable Attention-Based Deep Learning Model for Crime Prediction

Yeasir Rayhan, T. Hashem•Tue Dec 15 2020

AIST, an Attention-based Interpretable Spatio Temporal Network for crime prediction, which models the dynamic spatio-temporal correlations for a crime category based on past crime occurrences, external features and recurring trends of crime.

34 0

Paper Graph

Multi-axis Attentive Prediction for Sparse EventData: An Application to Crime Prediction

Yi Sui, Ga Wu, S. Sanner•Mon Oct 04 2021

A purely attentional approach to extract both short-term dynamics and long-term semantics of event propagation through two observation angles, and introduces a novel Frobenius norm-based contrastive learning objective to improve latent representational generalization.

2 0

Paper Graph

Crime prediction with graph neural networks and multivariate normal distributions

S. Tekin, S. Kozat•Sun Nov 28 2021

A new generative model applicable to any spatiotemporal data with graph convolutional gated recurrent units (Graph-ConvGRU) and multivariate Gaussian distributions is introduced and crime can be predicted in any resolution as the first time in the literature.

15 0

Paper Graph

Spatial-Temporal Sequential Hypergraph Network for Crime Prediction with Dynamic Multiplex Relation Learning

Lianghao Xia, Liefeng Bo, Yong Xu, Chao Huang, Peng Dai, Xiyue Zhang, Tianyi Chen•Sat Jul 31 2021

To handle spatial-temporal dynamics under the long-range and global context, the proposed ST-SHN framework designs a graph-structured message passing architecture with the integration of the hypergraph learning paradigm and introduces a multi-channel routing mechanism to learn the time-evolving structural dependency across crime types.

78 0

Paper Graph

Multi-Graph Fusion Networks for Urban Region Embedding

Shirui Pan, Chuanpan Zheng, Xiaoliang Fan, Shangbin Wu, Xu Yan, Shichao Zhu, Ming Cheng, Cheng Wang•Sun Jan 23 2022

This paper proposes multi-graph fusion networks (MGFN) to enable the cross domain prediction tasks, and designs the multi-level cross-attention mechanism to learn the comprehensive embeddings from multiple mobility patterns based on intra-pattern and inter-pattern messages.

68 0

Paper Graph

Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Prediction

Lianghao Xia, Chao Huang, Yong Xu, Zhonghang Li, Jiangsen Pei•Sun Apr 17 2022

This work proposes a Spatial-Temporal Self-Supervised Hypergraph Learning framework (ST-HSL), and designs the dual-stage self-supervised learning paradigm, to not only jointly capture local- and global-level spatial-temporal crime patterns, but also supplement the sparse crime representation by augmenting region self-discrimination.

93 0

Paper Graph

Explainable Spatio-Temporal Graph Neural Networks

Lianghao Xia, Chao Huang, Jiabin Tang•Fri Oct 20 2023

This work proposes an Explainable Spatio-temporal graph neural networks framework that enhances STGNNs with inherent explainability, enabling them to provide accurate predictions and faithful explanations simultaneously, and demonstrates that the STExplainer outperforms state-of-the-art baselines in terms of predictive accuracy and explainability metrics.

33 0

Paper Graph

Spatio-Temporal Meta Contrastive Learning

Lianghao Xia, Chao Huang, Jiabin Tang, Jie Hu•Fri Oct 20 2023

This work proposes a new spatio-temporal contrastive learning (CL4ST) framework to encode robust and generalizable STG representations via the STG augmentation paradigm and designs the meta view generator to automatically construct node and edge augmentation views for each disentangled spatial and temporal graph.

17 0

Paper Graph

Adding a benchmark result helps the community track progress.