Research map / Detection and segmentation / Tracking
ODONet: Online Dynamic Offset Network for Visual Object Tracking
Qinghua Liu, Wanli Xue, Shengyong Chen
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 DV-MFI (historical box as motion prompt) (ablation) | baseline tracker · GOT-10k | AO: 77.1 -> 77.6 | Improved |
| add ODOP deformable attention with online offsets (ablation) | baseline tracker · GOT-10k | AO: 77.1 -> 78.0 | Improved |
| combine DV-MFI and ODOP (ablation) | baseline tracker · GOT-10k | AO: 77.1 -> 78.9 | Improved |
| set online offset ratio w_on to 0.5 vs larger values (ablation) | ODOP · GOT-10k | AO: 78.9 vs 77.9 (0.75), 78.5 (1.00) | Improved |
| lower w_on to 0.25 (ablation) | ODOP · GOT-10k | AO: 78.9 -> 78.2 | Hurt |
| use larger input resolution 384 vs 224 | ODONet · LaSOT | AUC: 74.6 -> 75.1 | Improved |
| use larger input resolution 384 vs 224 | ODONet · LaSOText | AUC: 54.3 -> 53.1 | Hurt |
| add DV-MFI and ODOP: compute cost (ablation) | ODONet · GOT-10k | params/MACs: params 81.3M -> 90.8M, MACs 37.1G -> 37.7G, AO 77.1 -> 78.9 | Mixed |
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.
- MambaLCT — MambaLCT: Boosting Tracking via Long-term Context State Space Model (AAAI 2025) · better on 2 of 2 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
- OffsetNet: Towards Efficient Multiple Object Tracking, Detection, and Segmentation (TPAMI 2024 · similarity 0.88)
- OVTrack: Open-Vocabulary Multiple Object Tracking (CVPR 2023 · similarity 0.87)
- OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer (ICLR 2025 · similarity 0.86)
- Track-On: Transformer-based Online Point Tracking with Memory (ICLR 2025 · similarity 0.85)
- More Than Meets the Eye: Enhancing Multi-Object Tracking Even with Prolonged Occlusions (ICML 2025 · similarity 0.85)
- OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking (NeurIPS 2024 · similarity 0.85)
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.
