TY - GEN
T1 - DiffCrime
T2 - 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2024
AU - Wang, Shuliang
AU - Pan, Xinyu
AU - Ruan, Sijie
AU - Han, Haoyu
AU - Wang, Ziyu
AU - Yuan, Hanning
AU - Zhu, Jiabao
AU - Li, Qi
N1 - Publisher Copyright:
© 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.
PY - 2024/8/25
Y1 - 2024/8/25
N2 - Crime risk map plays a crucial role in urban planning and public security management. Traditionally, it is obtained solely from historical crime incidents or inferred from limited environmental factors, which are not sufficient to accurately model the occurrences of crimes over the geographical space well. Motivated by the impressive and realistic conditional generating power of diffusion models, in this paper, we propose a multimodal conditional diffusion method, namely, DiffCrime, to infer the crime risk map based on datasets in various domains, i.e., historical crime incidents, satellite imagery, and map imagery. It is equipped with a history-gated multimodal denoising network, i.e., HamNet, dedicated to the crime risk map inference. HamNet emphasizes the importance of historical crime data via a Gated-based History Fusion (GHF) module and adaptively controls multimodal conditions to be fused across different diffusion time steps via a Time step-Aware Modality Fusion (TAMF) module. Extensive experiments on two real-world datasets demonstrate the effectiveness of DiffCrime, which outperforms baselines by at least 43% and 31% in terms of RMSE, respectively.
AB - Crime risk map plays a crucial role in urban planning and public security management. Traditionally, it is obtained solely from historical crime incidents or inferred from limited environmental factors, which are not sufficient to accurately model the occurrences of crimes over the geographical space well. Motivated by the impressive and realistic conditional generating power of diffusion models, in this paper, we propose a multimodal conditional diffusion method, namely, DiffCrime, to infer the crime risk map based on datasets in various domains, i.e., historical crime incidents, satellite imagery, and map imagery. It is equipped with a history-gated multimodal denoising network, i.e., HamNet, dedicated to the crime risk map inference. HamNet emphasizes the importance of historical crime data via a Gated-based History Fusion (GHF) module and adaptively controls multimodal conditions to be fused across different diffusion time steps via a Time step-Aware Modality Fusion (TAMF) module. Extensive experiments on two real-world datasets demonstrate the effectiveness of DiffCrime, which outperforms baselines by at least 43% and 31% in terms of RMSE, respectively.
KW - conditional diffusion model
KW - crime risk map inference
KW - multimodal learning
UR - http://www.scopus.com/inward/record.url?scp=85203709413&partnerID=8YFLogxK
U2 - 10.1145/3637528.3671843
DO - 10.1145/3637528.3671843
M3 - Conference contribution
AN - SCOPUS:85203709413
T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
SP - 3212
EP - 3221
BT - KDD 2024 - Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
PB - Association for Computing Machinery
Y2 - 25 August 2024 through 29 August 2024
ER -
