Research map / Detection and segmentation / Tracking
VOVTrack: Exploring the Potentiality in Raw Videos for Open-Vocabulary Multi-Object Tracking
Zekun Qian, Ruize Han, Junhui Hou, Linqi Song, Wei Feng
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 prompt-guided attention (ablation) | VOVTrack · TAO validation (novel) | TETA: 29.8 -> 34.4 | Improved |
| add prompt-guided attention (ablation) | VOVTrack · TAO validation (base) | TETA: 35.7 -> 38.1 | Improved |
| add piecewise weight strategy (ablation) | VOVTrack · TAO validation (novel) | ClsA: 4.5 -> 6.0 | Improved |
| add self-supervised association learning (ablation) | VOVTrack · TAO validation (novel) | TETA: 31.3 -> 34.4 | Improved |
| add self-supervised association learning (ablation) | VOVTrack · TAO validation (base) | AssocA: 36.4 -> 38.8 | Improved |
| add short-long interval sampling (ablation) | VOVTrack · TAO validation (novel) | AssocA: 37.2 -> 39.2 | Improved |
| add category-aware clustering (ablation) | VOVTrack · TAO validation (base) | ClsA: 16.3 -> 17.5 | Improved |
| add intra-consistency loss (ablation) | VOVTrack · TAO validation (novel) | AssocA: 36.0 -> 39.2 | Improved |
| add inter-consistency loss (ablation) | VOVTrack · TAO validation (novel) | AssocA: 36.8 -> 39.2 | Improved |
| add short-long interval sampling (ablation) | VOVTrack · TAO validation (base) | ClsA: 17.7 -> 17.5 | Hurt |
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.
- 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
- OVTrack: Open-Vocabulary Multiple Object Tracking (CVPR 2023 · similarity 0.94)
- OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking (NeurIPS 2024 · similarity 0.94)
- OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer (ICLR 2025 · similarity 0.92)
- VastTrack: Vast Category Visual Object Tracking (NeurIPS 2024 · similarity 0.89)
- Multiple Object Tracking as ID Prediction (CVPR 2025 · similarity 0.89)
- SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Tracking (AAAI 2024 · similarity 0.88)
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.
