AI Paper Atlas

Research map / Detection and segmentation / Tracking

DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open Scenes

Shengyu Hao, Peiyuan Liu, Yibing Zhan, Kaixun Jin, Zuozhu Liu, Mingli Song, Jenq–Neng Hwang, Gaoang Wang

IJCV 2023 · Detection and segmentation › Tracking · approach: Memory and correlation-based MOT · 35 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 decoupled multi-head embedding (separate single-view and cross-view Re-ID heads) (ablation)CrossMOT · DIVOTrack easy test setCVMA: 70.7 -> 72.4Improved
add decoupled multi-head embedding (ablation)CrossMOT · DIVOTrack easy test setCVIDF1: 70.9 -> 71.1Improved
add conflict-free loss (ablation)CrossMOT · DIVOTrack easy test setCVMA: 70.1 -> 72.4Improved
add conflict-free loss (ablation)CrossMOT · DIVOTrack easy test setCVIDF1: 69.8 -> 71.1Improved
add decoupled multi-head embedding (ablation)CrossMOT · MvMHATCVMA: 92.2 -> 92.3Improved
add conflict-free loss (ablation)CrossMOT · MvMHATCVIDF1: 87.0 -> 87.4Improved
add conflict-free loss (ablation)CrossMOT · CAMPUSCVMA: 64.4 -> 65.6Improved
add decoupled multi-head embedding (ablation)CrossMOT · CAMPUSCVIDF1: 61.9 -> 61.2Hurt
vary single-view threshold delta_s from 0.1 to 0.4 with delta_c 0.3 or 0.5 (ablation)CrossMOT · DIVOTrack easy test setCVIDF1No clear effect
use joint detection and embedding (FairMOT) instead of separate detector trackerFairMOT vs Deepsort/CenterTrack/Tracktor/TraDes · DIVOTrack easy test setHOTA: 65.3 vs 48.4 to 58.9Improved
move from easy to hard test setsingle-view trackers · DIVOTrack hard test setHOTA: 65.3 -> 56.5Hurt
CrossMOT vs best baseline CTCrossMOT · DIVOTrack easy test setCVMA: 64.9 -> 72.4Improved

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