Research map / Detection and segmentation / Tracking
Re2EMA: Regularized and Reinitialized Exponential Moving Average for Target Model Update in Object Tracking
Jianglei Huang, Wengang Zhou
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add reinitialization term (return toward initial model) (ablation) | BACF EMA update · OTB-2015 | AUC (%): 62.77 -> 64.76 | Improved |
| add regularization term (ablation) | BACF EMA update · OTB-2015 | AUC (%): 62.77 -> 62.85 | Improved |
| add both regularization and reinitialization (ablation) | BACF · OTB-2015 | AUC (%): 63.24 -> 65.18 | Improved |
| use soft power-function g(p) instead of hard threshold q(p) (ablation) | Re2EMA on BACF · OTB-2015 | AUC (%): 63.16 -> 65.18 | Improved |
| use polynomial kernel instead of linear (ablation) | Re2EMA on BACF · OTB-2015 | AUC (%): 65.18 -> 65.42 | Improved |
| use Gaussian kernel instead of linear (ablation) | Re2EMA on BACF · OTB-2015 | AUC (%): 65.18 -> 65.22 | Improved |
| replace EMA update with Re2EMA | Staple · OTB-2015 | AUC (%): 58.63 -> 62.26 | Improved |
| replace EMA update with Re2EMA | SiamFC · OTB-2015 | AUC (%): 59.49 -> 62.24 | Improved |
| replace EMA update with Re2EMA | KCF · TColor-128 | AUC (%): 39.18 -> 39.58 | Improved |
| replace EMA update with Re2EMA | BACF · OTB-50 | AUC (%): 58.04 -> 60.75 | Improved |
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.
- Staple — Staple: Complementary Learners for Real-Time Tracking (CVPR 2016) · better on 1 of 1 shared result
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
- Track-On: Transformer-based Online Point Tracking with Memory (ICLR 2025 · similarity 0.85)
- TGFormer: Transformer with Track Query Group for Multi-Object Tracking (AAAI 2025 · similarity 0.84)
- Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers (CVPR 2024 · similarity 0.84)
- DiffusionTrack: Point Set Diffusion Model for Visual Object Tracking (CVPR 2024 · similarity 0.84)
- S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking (ICML 2025 · similarity 0.84)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.84)
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.
