Research map / Video / Video segmentation and tracking
PIP: Physical Interaction Prediction via Mental Simulation with Span Selection
Jiafei Duan, Samson Yu, Soujanya Poria, Bihan Wen, Cheston Tan
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 |
|---|---|---|---|
| add span selection (ablation) | PIP · SPACE+ Contact (seen) | accuracy (%): 61.84 -> 87.50 | Improved |
| add span selection (ablation) | PIP · SPACE+ Containment (seen) | accuracy (%): 80.39 -> 86.45 | Improved |
| add span selection (ablation) | PIP · SPACE+ Combined (seen) | accuracy (%): 58.70 -> 77.71 | Improved |
| add span selection (ablation) | PIP · SPACE+ Stability (seen) | accuracy (%): 92.18 -> 92.33 | No clear effect |
| add span selection (ablation) | PIP · SPACE+ Stability (unseen) | accuracy (%): 67.07 -> 66.41 | Hurt |
| add span selection (ablation) | PIP · SPACE+ Combined (unseen) | accuracy (%): 54.59 -> 62.23 | Improved |
| add span selection (ablation) | PIP · SPACE+ Contact (unseen) | accuracy (%): 52.14 -> 56.33 | Improved |
| add span selection (ablation) | PIP · SPACE+ Containment (unseen) | accuracy (%): 60.27 -> 55.99 | Hurt |
| use ConvLSTM mental simulation with span selection instead of PhyDNet | PIP · SPACE+ Combined (seen) | accuracy (%): 62.03 -> 77.71 | Improved |
| use ConvLSTM mental simulation with span selection instead of PhyDNet | PIP · SPACE+ Stability (seen) | accuracy (%): 92.36 -> 92.33 | No clear effect |
| add mental simulation and span selection to the no-simulation baseline | Baseline · SPACE+ Contact (seen) | accuracy (%): 65.63 -> 87.50 | Improved |
| add mental simulation and span selection to the no-simulation baseline | Baseline · SPACE+ Containment (unseen) | accuracy (%): 55.47 -> 55.99 | No clear effect |
Closest papers by meaning
- Visual Interaction Networks: Learning a Physics Simulator from Video (NeurIPS 2017 · similarity 0.87)
- Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects (CVPR 2020 · similarity 0.86)
- InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction (NeurIPS 2024 · similarity 0.86)
- FIction: 4D Future Interaction Prediction from Video (CVPR 2025 · similarity 0.85)
- Force Prompting: Video Generation Models Can Learn And Generalize Physics-based Control Signals (NeurIPS 2025 · similarity 0.85)
- InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation (CVPR 2025 · similarity 0.85)
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.
