AI Paper Atlas

Research map / Detection and segmentation / Tracking

OmniTracker: Unifying Visual Object Tracking by Tracking-With-Detection

Junke Wang, Zuxuan Wu, Dongdong Chen, Chong Luo, Xiyang Dai, Lu Yuan, Yu–Gang Jiang

TPAMI 2025 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 51 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 Reference-guided Feature Enhancement (RFE) (ablation)OmniTracker-T · TrackingNetNormalized precision: 80.9 -> 82.5Improved
add RFE (ablation)OmniTracker-T · DAVIS17J&F: 64.7 -> 66.2Improved
add RFE (ablation)OmniTracker-T · MOT17 valMOTA: 72.4 -> 73.2Improved
add RFE (ablation)OmniTracker-T · YTVIS19mAP: 58.5 -> 58.8Improved
add RFE, evaluated on DAVIS17 videos outside COCO categories (ablation)OmniTracker-T · DAVIS17 (non-COCO categories)J&F: 59.7 -> 61.9Improved
add ReID loss (ablation)OmniTracker-T · TrackingNetNormalized precision: 50.0 -> 82.5Improved
add ReID loss (ablation)OmniTracker-T · YTVIS19mAP: 35.8 -> 58.8Improved
add multi-frame memory bank (ablation)OmniTracker-T · DAVIS17J&F: 62.8 -> 66.2Improved
add Kalman filter at inference (ablation)OmniTracker-T · MOT17 valMOTA: 59.7 -> 73.2Improved
joint training across tasks instead of separate training (ablation)OmniTracker-T · DAVIS17J&F: 65.7 -> 66.2Improved
joint training instead of separate training (ablation)OmniTracker-T · TrackingNetNormalized precision: 82.0 -> 82.5Improved
ConvNeXt-Large backbone instead of Swin-Large (ablation)OmniTracker-L · MOT17MOTA: 79.1 -> 79.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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