Research map / Detection and segmentation / CNN features
Guided Interactive Video Object Segmentation Using Reliability-Based Attention Maps
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 |
|---|---|---|---|
| Use reliability-based attention to fuse information from multiple annotated frames (ablation) | GIS video object segmentation · DAVIS2017 validation | J&F score | Helped |
| Add intersection-aware propagation (ablation) | Baseline network using frame and interfused object features · DAVIS2017 validation | J&F-1st: 0.717 -> 0.737 | Helped |
| Add intersection-aware propagation (ablation) | Baseline network using frame and interfused object features · DAVIS2017 validation | J&F-3rd: 0.821 -> 0.832 | Helped |
| Replace IAP with local distance map propagation (ablation) | Baseline network · DAVIS2017 validation | J&F-1st: 0.717 -> 0.727 | Helped |
| Replace IAP with local transfer module (ablation) | Baseline network · DAVIS2017 validation | J&F-1st: 0.717 -> 0.730 | Helped |
| Use R-score guidance to select annotation frames (ablation) | Proposed GIS · DAVIS2017 validation | AUC-J: 0.817 -> 0.818 | Helped |
| Use four guided candidate frames rather than ground-truth selection (ablation) | Proposed GIS · DAVIS2017 validation | AUC-J&F: 0.853 -> 0.856 | Helped |
| Use R-score guidance to choose frames (ablation) | Proposed GIS in the user study · DAVIS2017 validation | SPV(s): 46.01 -> 34.59 | Helped |
| Use RS1 guidance instead of no R-score guidance (ablation) | Proposed GIS in the user study · DAVIS2017 validation | J&F: 0.794 -> 0.789 | Hurt |
| Use RS4 guidance instead of no R-score guidance (ablation) | Proposed GIS in the user study · DAVIS2017 validation | SPV(s): 46.01 -> 37.10 | Helped |
Closest papers by meaning
- Order-aware Interactive Segmentation (ICLR 2025 · similarity 0.86)
- AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation (ICLR 2024 · similarity 0.85)
- TETRIS: Towards Exploring the Robustness of Interactive Segmentation (AAAI 2024 · similarity 0.85)
- MFP: Making Full Use of Probability Maps for Interactive Image Segmentation (CVPR 2024 · similarity 0.84)
- Rethinking Interactive Image Segmentation with Low Latency High Quality and Diverse Prompts (CVPR 2024 · similarity 0.84)
- NTClick: Achieving Precise Interactive Segmentation With Noise-tolerant Clicks (CVPR 2025 · 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.