AI Paper Atlas

Research map / Video / Video segmentation and tracking

Incomplete Label Multi-Task Deep Learning for Spatio-Temporal Event Subtype Forecasting

Yuyang Gao, Liang Zhao, Lingfei Wu, Yanfang Ye, Hui Xiong, Chaowei Yang

AAAI 2019 · Video › Video segmentation and tracking · approach: Spatio-temporal predictive modeling · 27 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 spatial regularization term (SIMDA-SR vs SR) (ablation)Softmax regression · Brazil civil unrestmacro F1: 0.2247 -> 0.2560Improved
add spatial regularization term (SIMDA-SR vs SR) (ablation)Softmax regression · China air pollution, 1-daymacro F1: 0.4287 -> 0.5572Improved
add spatial regularization (SIMDA-3 vs SBM-3) (ablation)Shared-bottom model, 3 hidden layers · China air pollution, 1-daymacro F1: 0.5526 -> 0.6002Improved
add spatial regularization (SIMDA-1 vs SBM-1) (ablation)Shared-bottom model, 1 hidden layer · Brazil civil unrestmacro F1: 0.2696 -> 0.2788Improved
add spatial regularization (SIMDA-1 vs SBM-1) (ablation)Shared-bottom model, 1 hidden layer · China air pollution, 1-daymacro F1: 0.5812 -> 0.5560Hurt
add spatial regularization (SIMDA-3 vs SBM-3) (ablation)Shared-bottom model, 3 hidden layers · Colombia civil unrestmacro F1: 0.2863 -> 0.2710Hurt
add spatial regularization (SIMDA-3 vs SBM-3) (ablation)Shared-bottom model, 3 hidden layers · Venezuela civil unrestmacro F1: 0.2162 -> 0.2174Improved
add hidden layers (deep vs shallow models)SIMDA/MLP/SBM · civil unrest and China air datasetsmacro F1Improved
increase lead time from 1 to 7 daysSIMDA-3 · China air pollutionmacro F1: 0.6002 -> 0.5425Hurt
use SIMDA over SBMShared-bottom model · Brazil civil unrestAUC: 0.77 -> 0.81Improved
use hidden layers instead of softmax regression in SIMDA (ablation)SIMDA-SR · input dimensionality scalingruntime per ADMM step: around 26 seconds -> 6 seconds at 1300 dimensionsImproved

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