AI Paper Atlas

Research map / Video / Video segmentation and tracking

Spatio-Temporal Self-Organizing Map Deep Network for Dynamic Object Detection From Videos

Yang Du, Chunfeng Yuan, Bing Li, Weiming Hu, Stephen Maybank

CVPR 2017 · Video › Video segmentation and tracking · approach: Spatio-temporal predictive modeling · 14 citations (OpenAlex)

Check 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
Combine spatial and temporal weight updates and thresholds in STSOM (ablation)SOM background modeling · CDnet 2014 overallF-Measure: nearly 20 %Improved
Add temporal modeling to spatial-only SOM (ablation)SSOM · CDnet 2014 overallF-Measure: nearly 20 %Improved
Add spatial modeling to temporal-only SOM (ablation)TSOM · CDnet 2014 overallF-Measure: nearly 10 %Improved
Pre-train weights and learn thresholds before fine-tuning (ablation)STSOM on canoe · canoe, detection from frame 838F-MeasureImproved
Learn thresholds with Bayesian parameter estimation instead of using fixed thresholds (ablation)STSOM on canoe · canoe, detection from frame 838F-MeasureImproved
Stack additional STSOM layers (ablation)STSOM · canoe, frame 977detection performanceImproved

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