AI Paper Atlas

Research map / Detection and segmentation / Tracking

Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers

Tianyu Zhu, Markus Hiller, Mahsa Ehsanpour, Rongkai Ma, Tom W. Drummond, Ian D. Reid, Hamid Rezatofighi

TPAMI 2022 · Detection and segmentation › Tracking · approach: Memory and correlation-based MOT · 90 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
increase track history length from 1 to 30 (ablation)MO3TR · Validation set (MOT20 + 2DMOT15)MOTA: 55.4 -> 58.9Improved
increase track history length from 1 to 30 (ablation)MO3TR · Validation set (MOT20 + 2DMOT15)IDF1: 48.4 -> 50.6Improved
increase track history length from 1 to 30 (ablation)MO3TR · Validation set (MOT20 + 2DMOT15)FP: 4,700 -> 3,471Improved
increase track history length from 20 to 30 (ablation)MO3TR · Validation set (MOT20 + 2DMOT15)ML: 19 -> 20Hurt
add false-negative augmentation (two frames) (ablation)MO3TR · Validation set (MOT20 + 2DMOT15)MOTA: 12.2 -> 14.6Improved
add right-aligned insertion (two frames) (ablation)MO3TR · Validation set (MOT20 + 2DMOT15)MOTA: 14.6 -> 28.4Improved
add false-positive augmentation (two frames) (ablation)MO3TR · Validation set (MOT20 + 2DMOT15)MOTA: 28.4 -> 55.4Improved
add false-positive augmentation (30 frames) (ablation)MO3TR · Validation set (MOT20 + 2DMOT15)MOTA: 39.2 -> 58.9Improved
train on 30 frames instead of two frames (full augmentation) (ablation)MO3TR · Validation set (MOT20 + 2DMOT15)MOTA: 55.4 -> 58.9Improved
add false-negative augmentation to naive training (ablation)MO3TR · Validation set (MOT20 + 2DMOT15)IDF1: 22.1 -> 42.0Improved
predict initiation queries with multi-scale encoder (PIQ) (ablation)MO3TR · MOT17 test (private detections)MOTA: 63.9 -> 77.6Improved
predict initiation queries with multi-scale encoder (PIQ)MO3TR · MOT17 test (private detections)FPS: 11.9 -> 8.8Hurt

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