Research map / Video / Video segmentation and tracking
Efficient Video Object Segmentation via Network Modulation
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 |
|---|---|---|---|
| Fine-tune the modulated model on video data (Stage 2) | Ours on DAVIS 2016 · DAVIS 2016 | mean IU: 72.2 -> 74.0 | Helped |
| Add visual and spatial modulators instead of using one-shot fine-tuned baselines | Video object segmentation · DAVIS 2017 validation | J mean: 18.5 -> 52.5; 35.3 -> 52.5 | Mixed |
| Add a visual modulator | OSVOS with fixed segmentation weights · DAVIS 2017 validation | J mean: 18.5 -> 36.4 | Helped |
| Add a visual modulator | MaskTrack with fixed segmentation weights · DAVIS 2017 validation | J mean: 35.3 -> 44.6 | Helped |
| Add 100 iterations of online fine-tuning (ablation) | Ours · DAVIS 2017 | mean IU: 52.5 -> 60.8; +8.3 | Helped |
| Add CRF post-processing (ablation) | Ours · DAVIS 2017 | mean IU: 52.5 -> 54.4; +1.9 | Helped |
| Add a visual modulator (ablation) | Ours · DAVIS 2017 | mean IU: 33.0 -> 52.5; +19.5 | Helped |
| Add a spatial modulator (ablation) | Ours · DAVIS 2017 | mean IU: 40.1 -> 52.5; +12.4 | Helped |
| Add random crop augmentation (ablation) | Ours · DAVIS 2017 | mean IU: 50.6 -> 52.5; +1.9 | Helped |
| Add visual guide augmentation (ablation) | Ours · DAVIS 2017 | mean IU: 49.5 -> 52.5; +1.1 | Helped |
| Add spatial guide augmentation (ablation) | Ours · DAVIS 2017 | mean IU: 35.6 -> 52.5; +13.9 | Helped |
Closest papers by meaning
- Motion-Guided Cascaded Refinement Network for Video Object Segmentation (CVPR 2018 · similarity 0.88)
- Learning Video Object Segmentation From Static Images (CVPR 2017 · similarity 0.88)
- Deep Object Co-Segmentation via Spatial-Semantic Network Modulation (AAAI 2020 · similarity 0.87)
- Delving Deep Into Many-to-Many Attention for Few-Shot Video Object Segmentation (CVPR 2021 · similarity 0.87)
- Putting the Object Back into Video Object Segmentation (CVPR 2024 · similarity 0.86)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 2025 · similarity 0.85)
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.