Research map / Detection and segmentation / Tracking
Motion-Aware Object Tracking via Motion and Geometry-Aware Cues
Hongtao Yang, Bineng Zhong, Qihua Liang, Xiantao Hu, Yufei Tan, Haiying Xia, Shuxiang Song
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 |
|---|---|---|---|
| fuse geometric (depth) priors in layer 7 (ablation) | MoDTrack256 · LaSOT | AUC: 71.1 -> 71.3 | Improved |
| fuse geometric priors in layers 3 and 7 (ablation) | MoDTrack256 · LaSOT | AUC: 71.1 -> 71.7 | Improved |
| add motion pattern dictionary of size 100 (ablation) | MoDTrack256 · LaSOT | AUC: 71.1 -> 72.2 | Improved |
| increase dictionary size from 100 to 400 (ablation) | MoDTrack256 · LaSOT | AUC: 72.2 -> 72.6 | Improved |
| use attention-matrix matching instead of nearest neighbor (ablation) | MoDTrack256 · LaSOT | AUC: 72.6 -> 72.9 | Improved |
| add all modules (full MoDTrack256 vs baseline) (ablation) | MoDTrack256 · LaSOT | AUC: 71.1 -> 72.9 | Improved |
| use MoDTrack384 vs best prior tracker | MoDTrack384 · LaSOT | AUC: 73.2 -> 74.4 | Improved |
| MoDTrack384 vs TemTrack384 | MoDTrack384 · LaSOText | AUC: 53.4 vs 53.2 | Hurt |
| MoDTrack256 vs TemTrack256 | MoDTrack256 · LaSOText | AUC: 52.4 -> 52.4 | No clear effect |
| MoDTrack384 vs MambaLCT | MoDTrack384 · GOT-10k | SR0.5: 86.7 vs 86.4 | Hurt |
| MoDTrack256 vs MoDTrack384 resolution | MoDTrack · LaSOT | AUC: 72.9 -> 74.4 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- MambaLCT — MambaLCT: Boosting Tracking via Long-term Context State Space Model (AAAI 2025) · better on 1 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
- Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision (NeurIPS 2025 · similarity 0.88)
- Tracking through Severe Occlusion via Event-Derived Transient Cues (CVPR 2026 · similarity 0.88)
- TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation (NeurIPS 2024 · similarity 0.87)
- Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better (CVPR 2025 · similarity 0.87)
- ProMotion: Prototypes As Motion Learners (CVPR 2024 · similarity 0.86)
- Track-On: Transformer-based Online Point Tracking with Memory (ICLR 2025 · similarity 0.86)
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.
