Research map / 3D vision / 3D generation
Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions
Liang Xu, Chengqun Yang, Zili Lin, Fei Xu, Yifan Liu, Congsheng Xu, Yiyi Zhang, Jie Qin, Xingdong Sheng, Yunhui Liu, Xin Jin, Yichao Yan and 2 more
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 |
|---|---|---|---|
| use WHAM instead of other global motion estimators on egocentric video | Egocentric human motion estimation · InterVLA egocentric motion estimation | MPJPE: 589.9 -> 333.6 (vs GLAMR) | Improved |
| use TRACE instead of WHAM on PA-MPJPE | Egocentric human motion estimation · InterVLA egocentric motion estimation | PA-MPJPE: 103.2 -> 91.2 | Mixed |
| use HIMO instead of MDM for interaction synthesis | Human-object-human interaction synthesis · InterVLA interaction synthesis | FID: 2.8039 -> 0.6805 | Improved |
| use HIMO instead of priorMDM | Human-object-human interaction synthesis · InterVLA interaction synthesis | MModality: 2.1227 -> 1.1478 | Hurt |
| use semantic-graph CAHMP instead of MDM/InterDiff | Motion-based interaction prediction · InterVLA motion-based interaction prediction | Object translation error (mm): 138.7 -> 115.6 (vs InterDiff) | Improved |
| use InterDiff instead of MDM | Motion-based interaction prediction · InterVLA motion-based interaction prediction | Human joint error (mm): 175.3 -> 175.3 | No clear effect |
| use uncertainty-aware USST instead of FHOI | Vision-language interaction prediction · InterVLA vision-language interaction prediction | Average displacement error: 0.29 -> 0.24 | Improved |
Closest papers by meaning
- EARL: Towards a Unified Analysis-Guided Reinforcement Learning Framework for Egocentric Interaction Reasoning and Pixel Grounding (ICML 2026 · similarity 0.89)
- EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views (NeurIPS 2024 · similarity 0.89)
- ANNEXE: Unified Analyzing, Answering, and Pixel Grounding for Egocentric Interaction (CVPR 2025 · similarity 0.89)
- EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World (CVPR 2024 · similarity 0.89)
- Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos (CVPR 2026 · similarity 0.88)
- Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions? (ICLR 2025 · similarity 0.88)
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.
