AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Object-Centric Multiple Object Tracking

Zixu Zhao, Jiaze Wang, Max Horn, Yizhuo Ding, Tong He, Zechen Bai, Dominik Zietlow, Carl-Johann Simon-Gabriel, Bing Shuai, Zhuowen Tu, Thomas Brox, Bernt Schiele and 4 more

ICCV 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 14 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 object memory rollout instead of last tracks as index query (ablation)OC-MOT · CATERIDF1: 77.2% -> 88.6%Improved
use two MHA modules instead of dot-product similarity (ablation)OC-MOT index-merge · CATERIDF1: 72.0% -> 88.6%Improved
use two MHA instead of one shared MHA (ablation)OC-MOT index-merge · CATERIDF1: 86.2% -> 88.6%Improved
increase memory length Tmax from 6 to 32 (consecutive) (ablation)OC-MOT · CATERIDF1: 82.9% -> 88.4%Improved
use slow-fast sequence sampling instead of consecutive at Tmax=6 (ablation)OC-MOT · CATERIDF1: 82.9% -> 88.6%Improved
add 6.25% sparse mask labels with DETR loss to DINOSAUR grouping (ablation)DINOSAUR · FISHBOWLFG-ARIImproved
double number of annotated frames from 4 to 8 (ablation)DINOSAUR+DETR · FISHBOWLFG-ARI: +1.6%No clear effect
OC-MOT vs SAVi using object-centric associationSAVi · FISHBOWLIDF1: 46.9% -> 77.9%Improved
reconstruct optical flow instead of RGB in SAViSAVi · FISHBOWLIDF1: 46.9% -> 53.2%Mixed
unsupervised OC-MOT versus supervised MOTR on FISHBOWLOC-MOT · FISHBOWLIDF1: 81.6% -> 77.9%Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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