Research map / Detection and segmentation / Open-set and few-shot detection
PoseSOR: Human Pose Can Guide Our Attention
Huankang Guan, Rynson W.H. Lau
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| train with human pose labels (pose supervision) (ablation) | PoseSOR · ASSR (ablation setting) | SA-SOR: 0.665 -> 0.673 | Improved |
| add pose aggregation into salient object queries (ablation) | PoseSOR PAI module · ASSR (ablation setting) | SA-SOR: 0.667 -> 0.673 | Improved |
| add scene tokens (ablation) | PoseSOR PAI module · ASSR (ablation setting) | SA-SOR: 0.670 -> 0.673 | Improved |
| add instance-specific features feat_ins (ablation) | PoseSOR PAI module · ASSR (ablation setting) | SA-SOR: 0.669 -> 0.673 | Improved |
| use pose knowledge on images with no humans (ablation) | PoseSOR · ASSR images with no humans | SA-SOR: 0.596 -> 0.584 | No clear effect |
| use pose knowledge on images with at least one human (ablation) | PoseSOR · ASSR images with at least 1 human | SA-SOR: 0.709 -> 0.728 | Improved |
| use pose knowledge on images with two humans vs one (ablation) | PoseSOR · ASSR images by human count | SA-SOR: 1 human: 0.717 -> 0.722; 2 humans: 0.719 -> 0.745 | Improved |
| combine directional cues learning and rankings inference in PDR (ablation) | PoseSOR PDR module · ASSR (ablation setting) | SA-SOR: 0.666 -> 0.673 | Improved |
| add directional cues learning alone, without rankings inference (ablation) | PoseSOR PDR module · ASSR (ablation setting) | SA-SOR: 0.666 -> 0.661 | Hurt |
| increase shifting directions from 1 to 8 (ablation) | PoseSOR PDR module · ASSR (ablation setting) | SA-SOR: 0.670 -> 0.673 | Improved |
| increase shifting directions from 4 to 8 (ablation) | PoseSOR PDR module · ASSR (ablation setting) | SA-SOR: 0.673 -> 0.673 | No clear effect |
Later papers that compared with this method
2 later accepted papers report PoseSOR as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Salient Object Ranking via Cyclical Perception-Viewing Interaction Modeling (ICLR 2026 · better on 6 of 6 shared results)
- Probabilistic Salient Object Ranking (ICML 2026 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Probabilistic Salient Object Ranking (ICML 2026 · similarity 0.92)
- SeqRank: Sequential Ranking of Salient Objects (AAAI 2024 · similarity 0.90)
- Language-Guided Salient Object Ranking (CVPR 2025 · similarity 0.89)
- A Motion-aware Spatio-temporal Graph for Video Salient Object Ranking (NeurIPS 2024 · similarity 0.87)
- Exploring Pose-Aware Human-Object Interaction via Hybrid Learning (CVPR 2024 · similarity 0.86)
- Advancing Saliency Ranking with Human Fixations: Dataset Models and Benchmarks (CVPR 2024 · similarity 0.86)
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.
