Research map / Probabilistic and scientific modeling / Causal discovery
Reliable and Efficient Anytime Skeleton Learning
Rui Ding, Yanzhi Liu, Jingjing Tian, Zhouyu Fu, Shi Han, Dongmei Zhang
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 |
|---|---|---|---|
| run REAL with FD solver instead of without (NoFD) (ablation) | REAL · pathfinder | F0.5 / time: 0.818 -> 0.827; 208 -> 176 s | Improved |
| run REAL with FD solver instead of without (NoFD) (ablation) | REAL · diabetes | F0.5 / time: 0.690 -> 0.718; 760 -> 703 s | Improved |
| run REAL with FD solver instead of without (NoFD) (ablation) | REAL · pathfinder | precision: 0.970 -> 0.971 | Improved |
| run REAL with FD solver instead of without (NoFD) (ablation) | REAL · diabetes | precision: 0.834 -> 0.846 | Improved |
| use REAL instead of PC* for anytime skeleton learning | REAL · benchmark block 1 | precision at 30s: 0.832 -> 0.977 | Improved |
| use REAL instead of BLIP/MINOBS for anytime skeleton learning | REAL · benchmark block 3 | precision at 300s: 0.429 -> 0.971 | Improved |
| use REAL instead of BLIP/MINOBS on hepar2 and diabetes | REAL · hepar2, diabetes | F0.5 | No clear effect |
| use REAL instead of BLIP/MINOBS on BirdStrikes | REAL · BirdStrikes | Effect-StrikeX neighbors found: 1 -> 7 | Improved |
| use REAL instead of BLIP/MINOBS to find unique FD edges | REAL · pathfinder | FD edges missed: 5 -> 0 | Improved |
| use REAL instead of BLIP/MINOBS to find unique FD edges | REAL · diabetes | FD edges missed: 8 -> 0 | Improved |
Closest papers by meaning
- Latent Smooth Skeleton Embedding (AAAI 2017 · similarity 0.85)
- Progressive Skeletonization: Trimming more fat from a network at initialization (ICLR 2021 · similarity 0.85)
- Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition (CVPR 2025 · similarity 0.84)
- Motif Guided Graph Transformers with Combinatorial Skeleton Prototype Learning for Skeleton-Based Person Re-Identification (AAAI 2025 · similarity 0.83)
- Less is More: Compact-Token Masked Feature Learning for Skeleton Representation Learning (NeurIPS 2026 · similarity 0.82)
- Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning (CVPR 2024 · similarity 0.82)
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.
