Research map / 3D vision / Human pose estimation
HUMOF: Human Motion Forecasting in Interactive Social Scenes
Caiyi Sun, Yujing Sun, Xiao Han, Zemin Yang, Jiawei Liu, Xinge Zhu, SM Yiu, Yuexin Ma
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 HSI, HHI self and HHI relation hierarchical representations (ablation) | HUMOF · HOI-M3 ablation | mean path error (mm): 187.6 -> 174.6 | Improved |
| add HSI, HHI self and HHI relation hierarchical representations (ablation) | HUMOF · HOI-M3 ablation | mean pose error (mm): 123.2 -> 117.9 | Improved |
| add human-scene (HSI) representation (ablation) | HUMOF · HOI-M3 ablation | mean path error (mm): 183.7 -> 174.6 | Improved |
| add HHI self-encoding (ablation) | HUMOF · HOI-M3 ablation | mean path error (mm): 177.0 -> 174.6 | Improved |
| add HHI relation-encoding (ablation) | HUMOF · HOI-M3 ablation | mean path error (mm): 178.4 -> 174.6 | Improved |
| use coarse-to-fine injection instead of coarse-only (ablation) | HUMOF · HOI-M3 ablation | mean path error (mm): 182.7 -> 174.6 | Improved |
| use coarse-to-fine injection instead of fine-only (ablation) | HUMOF · HOI-M3 ablation | mean path error (mm): 182.4 -> 174.6 | Improved |
| use coarse-to-fine instead of multi-level injection (ablation) | HUMOF · HOI-M3 ablation | mean path error (mm): 177.1 -> 174.6 | Improved |
| add static DCT rescaling vector v (ablation) | HUMOF · HOI-M3 ablation | mean path error (mm): 178.9 -> 176.3 | Improved |
| add sample-adaptive vector alpha on top of v (ablation) | HUMOF · HOI-M3 ablation | mean path error (mm): 176.3 -> 174.6 | Improved |
| add sample-adaptive alpha alone (ablation) | HUMOF · HOI-M3 ablation | mean path error (mm): 178.9 -> 177.2 | Improved |
| coarse-only vs fine-only injection (ablation) | HUMOF · HOI-M3 ablation | mean pose error (mm): 121.2 vs 121.2 | No clear effect |
Closest papers by meaning
- Humans in Kitchens: A Dataset for Multi-Person Human Motion Forecasting with Scene Context (NeurIPS 2023 · similarity 0.89)
- Expressive Forecasting of 3D Whole-Body Human Motions (AAAI 2024 · similarity 0.89)
- Scene-aware Human Motion Forecasting via Mutual Distance Prediction (ECCV 2024 · similarity 0.88)
- MotionMap: Representing Multimodality in Human Pose Forecasting (CVPR 2025 · similarity 0.87)
- SimpliHuMoN: Simplifying Human Motion Prediction (NeurIPS 2026 · similarity 0.87)
- HuMoCon: Concept Discovery for Human Motion Understanding (CVPR 2025 · 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.
