Research map / Detection and segmentation / Tracking
Tracking Every Thing in the Wild
Siyuan Li, Martin Danelljan, Henghui Ding, Thomas E. Huang, Fisher Yu
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 Class Exemplar Matching to class-agnostic association (ablation) | TETer · BDD100K val | TETA: 49.7 -> 50.8 | Improved |
| add Class Exemplar Matching to class-agnostic association (ablation) | TETer · BDD100K val (Bus) | MOTA: 44.4 -> 48.2 | Improved |
| add Class Exemplar Matching to class-agnostic association (ablation) | TETer · BDD100K val (Rider) | MOTA: 35.9 -> 40.5 | Improved |
| add Class Exemplar Matching to class-agnostic association (ablation) | TETer · BDD100K val (Train) | TETA: 12.4 -> 14.4 | Improved |
| add Class Exemplar Matching to class-agnostic association (ablation) | TETer · BDD100K val | LocA: 47.8 -> 47.2 | Hurt |
| replace QDTrack hard class prior with TETer | TETer · BDD100K val (Bus) | TETA: 57.9 -> 63.7 | Improved |
| replace QDTrack hard class prior with TETer | TETer · TAO val (Rare classes) | TETA: 26.7 -> 30.1 | Improved |
| replace QDTrack with TETer | TETer · TAO val (All classes) | ClsA: 12.1 -> 13.2 | Mixed |
| increase TETA margin r from 50 to 90 (ablation) | TETer · TAO val | TETA: 33.2 -> 34.1 | Improved |
| increase TETA margin r from 50 to 90 (ablation) | QDTrack · TAO val | TETA: 30.0 -> 30.8 | Improved |
Closest papers by meaning
- Efficient Track Anything (ICCV 2025 · similarity 0.85)
- WATB: Wild Animal Tracking Benchmark (IJCV 2022 · similarity 0.82)
- Counting in the Wild (ECCV 2016 · similarity 0.80)
- GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild (TPAMI 2019 · similarity 0.78)
- Wild Animal Tracking with High-Quality Segment Anything Model and Domain Adaptation (IJCV 2026 · similarity 0.77)
- NetTrack: Tracking Highly Dynamic Objects with a Net (CVPR 2024 · similarity 0.74)
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.
