AI Paper Atlas

Research map / Video / Video segmentation and tracking

Bayesian Tracking of Video Graphs Using Joint Kalman Smoothing and Registration

Aditi Basu Bal, Ramy Mounir, Sathyanarayanan Aakur, Sudeep Sarkar, Anuj Srivastava

ECCV 2022 · Video › Video segmentation and tracking · approach: Physics-inspired motion prediction · 3 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 backward smoothing pass to Kalman filter (ablation)graph Kalman filter · Synthetic Dataset 1node L2 error: 0.009 -> 0.008Improved
add backward smoothing pass to Kalman filter (ablation)graph Kalman filter · Synthetic Dataset 1edge L2 error: 0.091 -> 0.091No clear effect
add backward smoothing pass to Kalman filter (ablation)graph Kalman filter · Synthetic Dataset 2node L2 error: 0.008 -> 0.006Improved
add backward smoothing pass to Kalman filter (ablation)graph Kalman filter · Synthetic Dataset 2edge L2 error: 0.084 -> 0.085No clear effect
replace median filter with Kalman smoothermedian filter · Synthetic Dataset 1node L2 error: 0.146 -> 0.008Improved
replace GRU multi-epoch training with Kalman smootherGRU · Synthetic Dataset 2edge L2 error: 0.493 -> 0.085Improved
add backward smoothing pass to Kalman filter (ablation)graph Kalman filter · MEVA clip 1rate of false detections: 0.721 -> 0.762Hurt
add backward smoothing pass to Kalman filter (ablation)graph Kalman filter · MEVA clip 2rate of false detections: 0.997 -> 0.956Improved
add backward smoothing pass to Kalman filter (ablation)graph Kalman filter · MEVA clip 3rate of missed detections: 3.580 -> 3.556Improved
replace median filter with Kalman smoothermedian filter · MEVA clip 1rate of false detections: 4.118 -> 0.762Improved

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