Research map / Video / Video segmentation and tracking
Tackling Background Distraction in Video Object Segmentation
Suhwan Cho, Heansung Lee, Minhyeok Lee, Chaewon Park, Sungjun Jang, Minjung Kim, Sangyoun Lee
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 swap-and-attach augmentation (ablation) | TBD · DAVIS 2017 val | G: 78.6 -> 80.0 | Improved |
| add overall and short/long-term templates to global+local matching (ablation) | TBD · DAVIS 2017 val | G: 77.2 -> 80.0 | Improved |
| add global+local (fine+coarse) matching to overall+temporal templates (ablation) | TBD · DAVIS 2017 val | G: 72.7 -> 80.0 | Improved |
| add short/long-term templates (ablation) | TBD · DAVIS 2017 val | G: 79.1 -> 80.0 | Improved |
| add overall template (ablation) | TBD · DAVIS 2017 val | G: 78.7 -> 80.0 | Improved |
| add spatial distance scoring instead of no spatial prior (ablation) | TBD · DAVIS 2017 val | G: 78.8 -> 80.0 | Improved |
| replace hard windowing (size 4) with learned distance scoring (ablation) | TBD · DAVIS 2017 val | G: 79.9 -> 80.0 | Improved |
| replace hard windowing (size 1) with learned distance scoring (ablation) | TBD · DAVIS 2017 val | G: 79.2 -> 80.0 | Improved |
| hard windowing size from 4 to 8 (ablation) | TBD · DAVIS 2017 val | G: 79.9 -> 78.5 | Hurt |
| hard windowing size from 1 to 4 (ablation) | TBD · DAVIS 2017 val | G: 79.2 -> 79.9 | Improved |
| use static images and TBD vs BMVOS no-static | TBD · DAVIS 2017 test-dev | G: 62.7 -> 66.0 | Improved |
| compare TBD with BMVOS speed | TBD · DAVIS 2016 val | fps: 45.9 -> 50.1 | Improved |
Closest papers by meaning
- Siamese Network with Interactive Transformer for Video Object Segmentation (AAAI 2022 · similarity 0.90)
- Learning Position and Target Consistency for Memory-Based Video Object Segmentation (CVPR 2021 · similarity 0.89)
- Exploring the Semi-Supervised Video Object Segmentation Problem from a Cyclic Perspective (IJCV 2022 · similarity 0.89)
- Learning Dynamic Network Using a Reuse Gate Function in Semi-Supervised Video Object Segmentation (CVPR 2021 · similarity 0.89)
- Video Object Segmentation Using Kernelized Memory Network With Multiple Kernels (TPAMI 2022 · similarity 0.88)
- Point-VOS: Pointing Up Video Object Segmentation (CVPR 2024 · similarity 0.88)
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.
