Research map / Detection and segmentation / Open-set and few-shot detection
Nonparametric Object and Parts Modeling With Lie Group Dynamics
David S. Hayden, Jason Pacheco, John W. Fisher III
Check 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 |
|---|---|---|---|
| Use Lie group dynamics and persistent part identities instead of independent per-frame part assignments | Nonparametric object and parts model · hand | MOTSA: 1.93 ± 0.8 -> 2.79 ± 0.30 | Improved |
| Use Lie group dynamics and persistent part identities instead of independent per-frame part assignments | Nonparametric object and parts model · spider | MOTSA: −4.4 ± 0.92 -> 3.44 ± 0.25 | Improved |
| Use Lie group dynamics and persistent part identities instead of independent per-frame part assignments | Nonparametric object and parts model · marmoset | MOTSA: −32.44 ± 2.78 -> 1.39 ± 0.89 | Improved |
| Use an unknown number of parts and Lie group dynamics rather than a known part count without Lie group dynamics | Nonparametric object and parts model · hand | MOTSA: 1.57 ± 0.44 -> 2.79 ± 0.30 | Improved |
| Use an unknown number of parts and Lie group dynamics rather than a known part count without Lie group dynamics | Nonparametric object and parts model · spider | MOTSA: 1.73 ± 0.31 -> 3.44 ± 0.25 | Improved |
| Use an unknown number of parts and Lie group dynamics rather than a known part count without Lie group dynamics | Nonparametric object and parts model · marmoset | MOTSA: 3.86 ± 0.17 -> 1.39 ± 0.89 | Hurt |
| Use an unknown number of parts and Lie group dynamics rather than a known part count without Lie group dynamics | Nonparametric object and parts model · marmoset | IDS: 0.43 ± 0.51 -> 1.24 ± 0.65 | Hurt |
Closest papers by meaning
- Articulation in Motion: Prior-free Part Mobility Analysis for Articulated Objects By Dynamic-Static Disentanglement (ICLR 2026 · similarity 0.90)
- SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology (NeurIPS 2026 · similarity 0.88)
- Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects (CVPR 2022 · similarity 0.88)
- Learning Implicit Representation for Reconstructing Articulated Objects (ICLR 2024 · similarity 0.88)
- Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting (ICLR 2025 · similarity 0.87)
- REACTO: Reconstructing Articulated Objects from a Single Video (CVPR 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.
