Research map / Video / Video segmentation and tracking
Gamifying Video Object Segmentation
Concetto Spampinato, Simone Palazzo, Daniela Giordano
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 spatio-temporal refinement of superclicks (ablation) | Gamified segmentation · Fish | F1: 0.680 -> 0.746 | Improved |
| add spatio-temporal refinement of superclicks (ablation) | Gamified segmentation · SegTrack v2 | F1: 0.716 -> 0.784 | Improved |
| add spatio-temporal refinement of superclicks (ablation) | Gamified segmentation · I2R | F1: 0.6304 -> 0.6484 | Improved |
| add spatio-temporal refinement of superclicks (ablation) | Gamified segmentation · ETH BIWI | F1: 0.613 -> 0.642 | Improved |
| use clicks from many players instead of one (ablation) | Gamified segmentation · ETH BIWI | F1: 0.379 -> 0.546 | Improved |
| use clicks from many players instead of one (ablation) | Gamified segmentation · 6+ objects per frame | F1: 0.310 -> 0.432 | Improved |
| use clicks from many players instead of one (ablation) | Gamified segmentation · I2R | F1: 0.438 -> 0.451 | No clear effect |
| increase cumulative play time from 1 h to 9 h (ablation) | Gamified segmentation · Fish | F1: 0.254 -> 0.746 | Improved |
| increase play time beyond about 7 h (ablation) | Gamified segmentation · SegTrack v2 | F1: 0.794 -> 0.784 | No clear effect |
| use click delay of 2 frames instead of 0 (ablation) | Gamified segmentation · Average of four datasets | average F1: 0.673 -> 0.705 | Improved |
| restrict to clicks of quality 0.8-1 instead of 0-0.6 (ablation) | Gamified segmentation · Fish | F1: 0.284 -> 0.558 | Improved |
| use interactive video annotation methods instead of this game within 50 secs | Interactive baselines · SegTrack v2 (10 frames) | POM (%): 39.8, 42.2, 61.5 vs 72.4 | Hurt |
Closest papers by meaning
- Fast User-Guided Video Object Segmentation by Interaction-And-Propagation Networks (CVPR 2019 · similarity 0.88)
- A Survey on Deep Learning Technique for Video Segmentation (TPAMI 2022 · similarity 0.87)
- Interactive Video Object Segmentation Using Global and Local Transfer Modules (ECCV 2020 · similarity 0.87)
- Fast and Accurate Online Video Object Segmentation via Tracking Parts (CVPR 2018 · similarity 0.87)
- SMITE: Segment Me In TimE (ICLR 2025 · similarity 0.86)
- Segment Any Motion in Videos (CVPR 2025 · 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.
