AI Paper Atlas

Research map / Detection and segmentation / Tracking

Non-Markovian Globally Consistent Multi-Object Tracking

Andrii Maksai, Xinchao Wang, Francois Fleuret, Pascal Fua

ICCV 2017 · Detection and segmentation › Tracking · approach: Memory and correlation-based MOT · 94 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 learned global non-Markovian patterns (supervised) to KSPKSP · people tracking datasets (average)IDF1: +0.16Improved
add learned global patterns (unsupervised) to KSPKSP · people tracking datasets (average)IDF1: +0.15Improved
add learned global patterns (supervised) to MDPMDP · people tracking datasets (average)IDF1: +0.05Improved
add learned global patterns to tracker, effect on MOTAKSP, MDP, RNN, SORT · people tracking datasets (average)MOTA: -0.01 to 0.06Mixed
add supervised patterns to BIPCC on Duke EasyBIPCC · Duke EasyIDF1: +1.1% IDFImproved
add supervised patterns to BIPCC on Duke HardBIPCC · Duke HardIDF1: +0.5% IDFImproved
add unsupervised patterns to BIPCC on Duke trainval-miniBIPCC · Duke trainval-miniIDF1: +0.9% IDFImproved
add supervised patterns to DM output on MOT16DM · MOT16 (two sequences)identity switches: 37% dropImproved
add unsupervised patterns to DM output on MOT16DM · MOT16 (two sequences)identity switches: 25% dropImproved
replace learned patterns with a pencil of lines in all directions (ablation)Ours · tracking datasetsIDF1/MOTAHurt
replace patterns with a Markovian local smoothness term (ablation)Ours · tracking datasetsIDF1/MOTAHurt
use 5 instead of 10 binary search iterations (ablation)Ours (supervised) · people tracking datasetsIDF1: 5 instead of 10; IDF1 change not more than 1%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