AI Paper Atlas

Research map / Detection and segmentation / Tracking

Learning a Neural Solver for Multiple Object Tracking

CVPR 2020 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 512 citations (OpenAlex)

Check 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
Use time-aware instead of vanilla node updates (ablation)Neural Solver · MOT17 validationIDF1: 67.3 -> 70.0Helped
Use time-aware instead of vanilla node updates (ablation)Neural Solver · MOT17 validationMOTA: 63.0 -> 64.0Helped
Use time-aware instead of vanilla node updates (ablation)Neural Solver · MOT17 validationconstraint satisfaction: 82.1 -> 98.8Helped
Add relative-position edge features to time-difference features (ablation)Neural Solver · MOT17 validationMOTA: 58.8 -> 63.6Helped
Add CNN appearance-distance features to time and relative-position features (ablation)Neural Solver · MOT17 validationIDF1: 68.7 -> 70.0Helped
Add CNN appearance-distance features to time and relative-position features (ablation)Neural Solver · MOT17 validationMOTA: 63.6 -> 64.0Helped
Use greedy rather than exact LP rounding (ablation)Neural Solver · MOT17 validationIDF1: 70.0 -> 69.8Hurt

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