Research map / Detection and segmentation / Tracking
[Re] Transparent Object Tracking Benchmark
Žiga Trojer
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 transparency features to ATOM | ATOM · TOTB | success (SUC): 0.641 -> 0.641; significant performance gains of 2.7% | Improved |
| Add transparency features to ATOM | ATOM · TOTB partial occlusion | success (SUC): 0.558 -> 0.635 | Improved |
| Add transparency features to ATOM | ATOM · TOTB scale variation | success (SUC): 0.568 -> 0.604 | Improved |
| Use ResNet-50 instead of ResNet-18 (ablation) | ATOM · TOTB | success (SUC): 0.614 -> 0.608 | Hurt |
| Use ResNet-50 instead of ResNet-18 (ablation) | DiMP · TOTB | success (SUC): 0.605 -> 0.594 | Hurt |
| Use ResNet-50 instead of ResNet-18 (ablation) | PrDiMP · TOTB | success (SUC): 0.639 -> 0.633 | Hurt |
| Use ResNet-50 instead of ResNet-18 (ablation) | SiamRPN++ · TOTB | success (SUC): 0.585 -> 0.617 | Improved |
| Use ResNet-50 instead of ResNet-18 (ablation) | TransATOM · TOTB | success (SUC): 0.641 -> 0.632 | Hurt |
| Add transparency features to ATOM (ablation) | ATOM · TOTB | success (SUC): 0.614 -> 0.625 | Improved |
| Add visual classification features to the transparency-only TransATOM-V (ablation) | TransATOM-V · TOTB | success (SUC): 0.625 -> 0.641 | Improved |
| Add transparency features to DiMP | DiMP · TOTB | success (SUC): 0.594 -> 0.613 ($\uparrow$1.9%) | Improved |
| Add transparency features to KYS | KYS · TOTB | success (SUC): 0.597 -> 0.619 ($\uparrow$2.2%) | 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 2 of 3 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 0.90)
- A Comprehensive Benchmark for Evaluating Night-time Visual Object Tracking (IJCV 2025 · similarity 0.86)
- A New Dataset and a Distractor-Aware Architecture for Transparent Object Tracking (IJCV 2024 · similarity 0.86)
- Need for Speed: A Benchmark for Higher Frame Rate Object Tracking (ICCV 2017 · similarity 0.86)
- LaSOT: A High-quality Large-scale Single Object Tracking Benchmark (IJCV 2020 · similarity 0.85)
- VastTrack: Vast Category Visual Object Tracking (NeurIPS 2024 · similarity 0.83)
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.
