AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

STREETS: A Novel Camera Network Dataset for Traffic Flow

NeurIPS 2019 · Graph learning › Knowledge and temporal graphs · approach: Spatio-temporal graph traffic forecasting · 26 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add 2-hop neighbor camera data (K=2) to the features instead of own camera only (K=0) (ablation)SVR, RFR, LR · STREETS 15 min horizonMAEc/MAE: 3.05/3.25 -> 2.96/3.20 (SVR, 7/16)Helped
Add 2-hop neighborhood to ANN features (ablation)ANN · STREETS 15 min horizonMAEc/MAE: 3.21/3.40 -> 3.52/3.73 (7/16)Hurt
Condition predictions on queue vs free-flow state (MAEc instead of MAE) (ablation)SVR, RFR, LR · STREETSMAE: 3.25 -> 3.05 (SVR K=0, 7/16, 15 min)Helped
Use nonlinear models (RFR, SVR) instead of linear regressiontraffic prediction · STREETSMAE: 4.80/5.05 -> 4.07/4.28 (LR vs SVR, 7/15, K=0, L=3)Helped
Increase history length L from 3 to 6 (ablation)SVR · STREETS 15 min horizonMAEc/MAE: 3.05/3.25 -> 3.14/3.32 (K=0, 7/16)No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy