Research map / Detection and segmentation / Tracking
"HVC-Net: Unifying Homography, Visibility, and Confidence Learning for Planar Object Tracking"
Haoxian Zhang, Yonggen Ling
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 correlation block (D) (ablation) | Ours w/o DPMR · Synthetic MS-COCO test set | AE: 6.678 -> 4.173 | Improved |
| add pyramids (P) to correlation block model (ablation) | Ours-D · Synthetic MS-COCO test set | AE: 4.173 -> 1.145 | Improved |
| add pyramids (P) without correlation block (ablation) | Ours w/o DPMR · Synthetic MS-COCO test set | AE: 6.678 -> 5.280 | Improved |
| add refinement module (R) (ablation) | Ours-DP · Synthetic MS-COCO test set | AE: 1.145 -> 0.876 | Improved |
| add refinement module (R) (ablation) | Ours-P · Synthetic MS-COCO test set | AE: 5.280 -> 2.970 | Improved |
| add joint visibility learning (M) (ablation) | Ours-DP · Synthetic MS-COCO test set | AE: 1.145 -> 1.097 | Improved |
| add joint visibility learning (M) (ablation) | Ours-P · Synthetic MS-COCO test set | AE: 5.280 -> 4.051 | Improved |
| add joint visibility learning (M) to refined model (ablation) | Ours-DPR · Synthetic MS-COCO test set | HD: 1.739 -> 1.695 | Improved |
| add refinement module (R) (ablation) | Ours-DPM · Synthetic MS-COCO test set | HD: 2.107 -> 1.695 | Improved |
| add correlation block (D) for visibility (ablation) | Ours-PMR · Synthetic test set, visibility | visibility loss: 0.346 -> 0.328 | Improved |
| learn visibility jointly (M) rather than independently (V) (ablation) | Ours-DPVR · Synthetic test set, visibility | visibility loss: 0.335 -> 0.328 | Improved |
| use OursCon (cost-volume confidence) instead of PatchCon | Ours-DPMR · Confidence classification | FPR: 14.5% -> 8.7% | Improved |
Closest papers by meaning
- Homography Decomposition Networks for Planar Object Tracking (AAAI 2022 · similarity 0.90)
- Segmentation-Guided Homography Estimation for Long-Term Planar Tracking (ECCV 2026 · similarity 0.88)
- PlanarTrack: A Large-scale Challenging Benchmark for Planar Object Tracking (ICCV 2023 · similarity 0.87)
- Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision (NeurIPS 2025 · similarity 0.87)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 2024 · similarity 0.86)
- UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation (AAAI 2024 · 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.
