Research map / Video / Video segmentation and tracking
Reliable Propagation-Correction Modulation for Video Object Segmentation
Read the paperCheck 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 |
|---|---|---|---|
| Add a correction modulator after propagation modulation (P2C) (ablation) | Ours · YouTube-VOS 2018 Validation | J&F: 82.3 -> 82.9 | Helped |
| Use propagation-then-correction rather than correction-then-propagation (ablation) | Ours · YouTube-VOS 2018 Validation | J&F: 82.5 -> 82.9 | Helped |
| Use cascaded propagation and correction rather than parallel P&C (ablation) | Ours · YouTube-VOS 2018 Validation | J&F: 82.5 -> 82.9 | Helped |
| Add correction guidance through a self-then-correction cascade rather than two self-modulators (ablation) | Ours · YouTube-VOS 2018 Validation | J&F: 81.9 -> 82.6 | Helped |
| Stack additional propagation modulators instead of relying on correction guidance (ablation) | Ours · YouTube-VOS 2018 Validation | J&F: P2P 82.3; P2P2P 82.3 | No clear effect |
| Add object proxy augmentation for modulation weights (ablation) | P2C · YouTube-VOS 2019 Validation | J&F: 82.7 -> 82.9 | Helped |
| Use augmented object proxies for both modulation weights and similarity (ablation) | P2C · YouTube-VOS 2019 Validation | J&F: 82.9 -> 83.6 | Helped |
| Add reliability filtering to augmented object proxies (ablation) | P2C with OA(W+S) · YouTube-VOS 2019 Validation | J&F: 83.6 -> 83.9 | Helped |
| Replace no reliability measure with logit-based reliability (ablation) | P2C · YouTube-VOS 2019 | J&F: 82.69 -> 82.75 | No clear effect |
| Use Shannon entropy instead of logit-based reliability (ablation) | P2C · YouTube-VOS 2019 | J&F: 82.75 -> 83.92 | Helped |
| Use full-resolution testing instead of standard-resolution testing | Ours · DAVIS17 Test-dev | J&F: 79.2 -> 81.0 | Helped |
Closest papers by meaning
- Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation (NeurIPS 2020 · similarity 0.86)
- Accelerating Video Object Segmentation With Compressed Video (CVPR 2022 · similarity 0.86)
- Per-Clip Video Object Segmentation (CVPR 2022 · similarity 0.86)
- Holistic Correction with Object Prototype for Video Object Segmentation (AAAI 2025 · similarity 0.85)
- Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation (AAAI 2024 · similarity 0.84)
- When Trackers Fail: VLM-Guided Verification and Recovery for Robust Video Object Segmentation (NeurIPS 2026 · similarity 0.84)
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.