Research map / Detection and segmentation / Tracking
RGBD1K: A Large-Scale Dataset and Benchmark for RGB-D Object Tracking
Xue-Feng Zhu, Tianyang Xu, Zhangyong Tang, Zucheng Wu, Haodong Liu, Xiao Yang, Xiao-Jun Wu, Josef Kittler
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 |
|---|---|---|---|
| fine-tune STARK-S on RGBD1K RGB images only (ablation) | STARK-S · RGBD1K test set | F-score: 0.495 -> 0.522 | Improved |
| train SPT with RGB-D images from RGBD1K rather than RGB-only fine-tuning (ablation) | STARK-S · RGBD1K test set | F-score: 0.522 -> 0.561 | Improved |
| train on RGBD1K RGB-D data (ablation) | STARK-S · DepthTrack | F-score: 0.500 -> 0.538 | Improved |
| train on RGBD1K RGB-D data (ablation) | STARK-S · CDTB | F-score: 0.664 -> 0.688 | Improved |
| add a 2-layer transformer encoder after Fusion A (ablation) | SPT feature fusion · RGBD1K | F-score: 0.530 -> 0.561; 5.8% | Improved |
| add a 2-layer transformer encoder after Fusion A (ablation) | SPT feature fusion · CDTB | F-score: 0.675 -> 0.688; 1.9% | Improved |
| add an RGB-feature skip connection to Fusion A (ablation) | SPT feature fusion · RGBD1K | F-score: 0.530 -> 0.531 | No clear effect |
| add an RGB-feature skip connection to Fusion B (ablation) | SPT feature fusion · RGBD1K | F-score: 0.561 -> 0.563 | No clear effect |
| add an RGB-feature skip connection to Fusion A (ablation) | SPT feature fusion · CDTB | F-score: 0.675 -> 0.680 | Improved |
| add an RGB-feature skip connection to Fusion B (ablation) | SPT feature fusion · CDTB | F-score: 0.688 -> 0.681 | Hurt |
Closest papers by meaning
- Single-Model and Any-Modality for Video Object Tracking (CVPR 2024 · similarity 0.89)
- Revisiting motion information for RGB-Event tracking with MOT philosophy (NeurIPS 2024 · similarity 0.88)
- VastTrack: Vast Category Visual Object Tracking (NeurIPS 2024 · similarity 0.88)
- CSTrack: Enhancing RGB-X Tracking via Compact Spatiotemporal Features (ICML 2025 · similarity 0.87)
- Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm (NeurIPS 2025 · similarity 0.87)
- SUTrack: Towards Simple and Unified Single Object Tracking (AAAI 2025 · similarity 0.87)
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.
