Research map / Video / Video segmentation and tracking
Accelerating Video Object Segmentation With Compressed Video
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 |
|---|---|---|---|
| Accelerate STCN using compressed-video propagation and correction | STCN · DAVIS17 validation | FPS: 20.2 -> 33.7 | Helped |
| Accelerate STCN using compressed-video propagation and correction | STCN · DAVIS17 validation | J&F: 85.3 -> 82.4 | Hurt |
| Accelerate MiVOS using compressed-video propagation and correction | MiVOS · YouTube-VOS 2018 validation | J_s: 81.1 -> 78.9 | Hurt |
| Accelerate MiVOS using compressed-video propagation and correction | MiVOS · YouTube-VOS 2018 validation | FPS: †13 -> 45.9 | Helped |
| Use bidirectional motion-vector warping instead of unidirectional optical-flow warping (ablation) | MiVOS propagation · DAVIS16 | J: 77.4 -> 85.7 | Helped |
| Add soft propagation and noise suppression to motion-vector warping (ablation) | MiVOS propagation · DAVIS17 | J: 77.2 -> 79.7 | Helped |
| Add the learned decoder to motion-vector warping (ablation) | MiVOS propagation · DAVIS16 | J: 85.7 -> 88.3 | Helped |
| Add confidence-based suppression of propagated predictions (ablation) | MiVOS propagation · DAVIS16 | J: 88.3 -> 88.8 | Helped |
| Add residual-based mask correction (ablation) | MiVOS propagation · DAVIS17 | J: 79.6 -> 79.7 | Helped |
| Reduce keyframes to approximately 25% using B-frame-biased encoding (ablation) | MiVOS + CoVOS · DAVIS16 | J&F: 89.4 -> 85.1 | Hurt |
| Reduce keyframes to approximately 13% using uniform B-frame encoding (ablation) | MiVOS + CoVOS · DAVIS16 | J&F: 89.4 -> 82.9 | Hurt |
Closest papers by meaning
- From ViT Features to Training-free Video Object Segmentation via Streaming-data Mixture Models (NeurIPS 2023 · similarity 0.89)
- Learning Dynamic Network Using a Reuse Gate Function in Semi-Supervised Video Object Segmentation (CVPR 2021 · similarity 0.88)
- Per-Clip Video Object Segmentation (CVPR 2022 · similarity 0.88)
- A Transductive Approach for Video Object Segmentation (CVPR 2020 · similarity 0.88)
- Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation (NeurIPS 2020 · similarity 0.88)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025 · similarity 0.87)
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.