Research map / Detection and segmentation / CNN features
Bi-Directional Object-Context Prioritization Learning for Saliency Ranking
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 |
|---|---|---|---|
| Add SOS and OCOR modules (ablation) | Saliency ranking model · ASSR | SOR: 0.837 -> 0.904 | Helped |
| Add SOS (ablation) | Saliency ranking model · ASSR | SOR: 0.885 -> 0.904 | Helped |
| Add OCOR (ablation) | Saliency ranking model · ASSR | SOR: 0.870 -> 0.904 | Helped |
| Add GCP alone (ablation) | SOS baseline · ASSR | SOR: 0.837 -> 0.840 | Helped |
| Add DR alone (ablation) | SOS baseline · ASSR | SOR: 0.837 -> 0.857 | Helped |
| Add GCP and DR together (ablation) | SOS baseline · ASSR | SOR: 0.837 -> 0.870 | Helped |
| Use concatenation and two convolutional layers for object-context relations (S1) (ablation) | OCOR baseline · ASSR | SOR: 0.837 -> 0.842 | Helped |
| Add channel-wise attention to S1 (S2) (ablation) | OCOR baseline · ASSR | SOR: 0.842 -> 0.845 | Helped |
| Add spatial-wise attention to S1 (S3) (ablation) | OCOR baseline · ASSR | SOR: 0.842 -> 0.853 | Helped |
| Add channel-wise and spatial-wise attention to S1 (S4) (ablation) | OCOR baseline · ASSR | SOR: 0.842 -> 0.857 | Helped |
| Replace alternative relation strategy with the proposed OCOR module (ablation) | Object-context relation model · ASSR | SOR: 0.857 -> 0.885 | Helped |
| Use bi-directional object-context prioritization learning | Saliency ranking · ASSR and IRSR Test Sets | SOR: ASSR: 0.904; IRSR: 0.834 | Helped |
Closest papers by meaning
- Inferring Attention Shift Ranks of Objects for Image Saliency (CVPR 2020 · similarity 0.92)
- Language-Guided Salient Object Ranking (CVPR 2025 · similarity 0.91)
- SeqRank: Sequential Ranking of Salient Objects (AAAI 2024 · similarity 0.89)
- Explainable Saliency: Articulating Reasoning with Contextual Prioritization (CVPR 2025 · similarity 0.88)
- CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion (AAAI 2025 · similarity 0.88)
- A Motion-aware Spatio-temporal Graph for Video Salient Object Ranking (NeurIPS 2024 · 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.
