Research map / 3D vision / Human pose estimation
Transferring Objects: Joint Inference of Container and Human Pose
Hanqing Wang, Wei Liang, Lap-Fai Yu
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 the psi_s stability term (ablation) | full model · Container+pose ranking (Total test set) | Top 12 ranking accuracy: 49.24% -> 66.67% | Improved |
| add the phi_c convenience term (ablation) | full model · Container+pose ranking (Total test set) | Top 12 ranking accuracy: 40.15% -> 66.67% | Improved |
| add the psi_c containability term (ablation) | full model · Container+pose ranking (Total test set) | Top 12 ranking accuracy: 64.39% -> 66.67% | No clear effect |
| add the psi_e efficiency term (ablation) | full model · Container+pose ranking (Total test set) | Top 12 ranking accuracy: 64.39% -> 66.67% | No clear effect |
| add the phi_e energy term (ablation) | full model · Container+pose ranking (Total test set) | Top 12 ranking accuracy: 68.18% -> 66.67% | Hurt |
| add the phi_e energy term (ablation) | full model · Container+pose ranking (Middle test set) | Top 12 ranking accuracy: 75.61% -> 65.85% | Hurt |
| add the phi_e energy term (ablation) | full model · Container+pose ranking (Large test set) | Top 12 ranking accuracy: 100.00% -> 100.00% | No clear effect |
| add the psi_s stability term (ablation) | full model · Container+pose ranking (Small test set) | Top 12 ranking accuracy: 47.67% -> 65.12% | Improved |
| add the phi_c convenience term (ablation) | full model · Container+pose ranking (Middle test set) | Top 12 ranking accuracy: 34.15% -> 65.85% | Improved |
| add the psi_s stability term (ablation) | full model · Container+pose ranking (Total test set) | Top 3 ranking accuracy: 9.85% -> 18.18% | Improved |
| add the phi_c convenience term (ablation) | full model · Container+pose ranking (Total test set) | Top 24 ranking accuracy: 81.82% -> 92.42% | Improved |
Closest papers by meaning
- Object Pop-Up: Can We Infer 3D Objects and Their Poses From Human Interactions Alone? (CVPR 2023 · similarity 0.87)
- BOP-ASK: Object-Interaction Reasoning for Vision-Language Models (CVPR 2026 · similarity 0.84)
- InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing (CVPR 2025 · similarity 0.84)
- Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer (CVPR 2024 · similarity 0.84)
- Forecasting of 3D Whole-body Human Poses with Grasping Objects (CVPR 2024 · similarity 0.84)
- Reconstructing People, Places, and Cameras (CVPR 2025 · similarity 0.84)
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.
