Research map / Detection and segmentation / Tracking
A New Dataset and a Distractor-Aware Architecture for Transparent Object Tracking
Alan Lukežič, Ziga Trojer, Jiří Matas, Matej Kristan
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 |
|---|---|---|---|
| train on Trans2k in addition to opaque datasets | DiMP · TOTB | AUC: improves by over 16% | Improved |
| train on Trans2k with segmentation ground truth | D3S · TOTB | AUC: gains a remarkable 6% | Improved |
| train on Trans2k | STARK · TOTB | AUC: additional performance boost of 2.5% | Improved |
| train on Trans2k | TransATOM · TOTB | AUC: gains 3.3% | Improved |
| train ATOM on Trans2k instead of adding the TransATOM method modifications | ATOM · TOTB | AUC: outperforms this extension by 1.7% | Improved |
| add fine-tuning on transparent objects (Trans2k) (ablation) | DiTra · TOTB | AUC: reduces the tracking performance by 4.5% | Improved |
| add distractor-aware feature extraction branch (ablation) | DiTra · TOTB | AUC: causes a 5% performance drop | Improved |
| add pose-aware feature extraction branch (ablation) | DiTra · TOTB | AUC: reduces the performance by 2% | Improved |
| add most recent template in distractor-aware branch (ablation) | DiTra · TOTB | AUC: reduces the tracking performance by approximately 1% | Improved |
| use DiTra instead of second-best STARK and TOMP | DiTra · TOTB | AUC: outperforms the second-best STARK and TOMP for approximately 5% in AUC | Improved |
| use DiTra instead of STARK on opaque VOT2020 | DiTra · VOT2020 | EAO: outperforms the second-best STARK by 2% EAO | Improved |
| use DiTra instead of MixFormer on opaque GoT10k | DiTra · GoT10k test | AUC: 73.2 -> 76.1 | Improved |
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.
- ATOM — ATOM: Accurate Tracking by Overlap Maximization (CVPR 2019) · better on 4 of 5 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
- Transparent Object Tracking Benchmark (ICCV 2021 · similarity 0.91)
- A Distractor-Aware Memory for Visual Object Tracking with SAM2 (CVPR 2025 · similarity 0.89)
- Know Your Surroundings: Exploiting Scene Information for Object Tracking (ECCV 2020 · similarity 0.89)
- Distractor-Aware Memory-Based Visual Object Tracking (IJCV 2026 · similarity 0.88)
- Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision (NeurIPS 2025 · similarity 0.86)
- DiffusionTrack: Diffusion Model for Multi-Object Tracking (AAAI 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.
