Research map / Detection and segmentation / Tracking
COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm
Zekun Qian, Wei Feng, Ruize Han, Junhui Hou
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 |
|---|---|---|---|
| COVTrack++ over COVTrack under C-TAO training | COVTrack · TAO val (novel classes) | TETA: 34.3 -> 35.4 | Improved |
| COVTrack++ over COVTrack under C-TAO training | COVTrack · TAO test (novel classes) | TETA: 28.9 -> 30.5 | Improved |
| COVTrack++ over COVTrack under C-TAO training | COVTrack · TAO test (novel classes) | AssocA: 32.6 -> 35.8 | Improved |
| COVTrack++ over COVTrack under C-TAO training | COVTrack · TAO val (novel classes) | AssocA: 41.3 -> 42.6 | Improved |
| train OVTrack on continuous C-TAO annotations | OVTrack · TAO val (novel classes) | TETA: 27.8 -> 30.5 | Improved |
| train OVTR on continuous C-TAO annotations | OVTR · TAO val (novel classes) | TETA: 31.4 -> 32.5 | Improved |
| train TETer on continuous C-TAO annotations | TETer · TAO val (novel classes) | TETA: 25.7 -> 26.7 | Improved |
| train QDTrack on continuous C-TAO annotations | QDTrack · TAO val (novel classes) | TETA: 22.5 -> 23.2 | Improved |
| train OVTrack on continuous C-TAO annotations | OVTrack · TAO test (novel classes) | TETA: 24.1 -> 25.3 | Improved |
| COVTrack++ over OVTR on classification accuracy | OVTR · TAO val (novel classes) | ClsA: 5.4 -> 3.5 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- OVTR — OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer (ICLR 2025) · better on 1 of 2 shared results
- OVTrack — OVTrack: Open-Vocabulary Multiple Object Tracking (CVPR 2023) · 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
- COVTrack: Continuous Open-Vocabulary Tracking via Adaptive Multi-Cue Fusion (ICCV 2025 · similarity 0.95)
- OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking (NeurIPS 2024 · similarity 0.92)
- OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer (ICLR 2025 · similarity 0.91)
- Multiple Object Tracking as ID Prediction (CVPR 2025 · similarity 0.90)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.90)
- Focusing on Tracks for Online Multi-Object Tracking (CVPR 2025 · similarity 0.90)
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.
