Research map / Video / Video segmentation and tracking
FusionSeg: Learning to Combine Motion and Appearance for Fully Automatic Segmentation of Generic Objects in Videos
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Combine appearance and motion streams instead of using appearance alone (ablation) | FusionSeg · DAVIS | Avg. IoU: 64.69 -> 71.51 | Helped |
| Combine appearance and motion streams instead of using motion alone (ablation) | FusionSeg · DAVIS | Avg. IoU: 60.18 -> 71.51 | Helped |
| Combine appearance and motion streams instead of using appearance alone (ablation) | FusionSeg · YouTube-Objects | Avg. IoU: 68.57 -> 68.43 | No clear effect |
| Combine appearance and motion streams instead of using motion alone (ablation) | FusionSeg · YouTube-Objects | Avg. IoU: 49.43 -> 68.43 | Helped |
| Add motion to the appearance stream (ablation) | FusionSeg · YouTube-Objects, Top 10% moving | IoU: 71.58 -> 72.34 | Helped |
| Add motion to the appearance stream (ablation) | FusionSeg · YouTube-Objects, Top 10% static | IoU: 61.79 -> 59.86 | Hurt |
| Combine appearance and motion streams instead of using appearance alone (ablation) | FusionSeg · Segtrack-v2 | Avg. IoU: 56.88 -> 61.40 | Helped |
| Combine appearance and motion streams instead of using motion alone (ablation) | FusionSeg · Segtrack-v2 | Avg. IoU: 53.04 -> 61.40 | Helped |
| Use learned motion and appearance fusion rather than simple optical-flow thresholding | FusionSeg · DAVIS | Avg. IoU: 42.95 -> 71.51 | Helped |
Closest papers by meaning
- A Generative Appearance Model for End-To-End Video Object Segmentation (CVPR 2019 · similarity 0.87)
- Learning Motion Patterns in Videos (CVPR 2017 · similarity 0.87)
- Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation (CVPR 2022 · similarity 0.87)
- Breaking the "Object" in Video Object Segmentation (CVPR 2023 · similarity 0.86)
- DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping (CVPR 2021 · similarity 0.86)
- Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation (CVPR 2023 · 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.