Research map / 3D vision / Human pose estimation
GIMO: Gaze-Informed Human Motion Prediction in Context
Yang Zheng, Yanchao Yang, Kaichun Mo, Jiaman Li, Tao Yu, Yebin Liu, Karen Liu, Leonidas J. Guibas
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 gaze input to RNN (ablation) | RNN · GIMO destination error (known scenes) | global translation error: 0.538 -> 0.389 | Improved |
| add gaze input to MultimodalNet (ablation) | MultimodalNet · GIMO destination error (known scenes) | global translation error: 0.442 -> 0.316 | Improved |
| add gaze input to MultimodalNet (ablation) | MultimodalNet · GIMO destination error (new scenes) | MPJPE: 236.0 -> 204.9 | Improved |
| add gaze input to RNN (ablation) | RNN · GIMO path error (new scenes) | MPJPE: 180.3 -> 182.6 | Hurt |
| add gaze input to MultimodalNet (ablation) | MultimodalNet · GIMO path error (known scenes) | MPJPE: 190.0 -> 193.1 | Hurt |
| use bidirectional cross-modal fusion instead of MultimodalNet+gaze (ablation) | MultimodalNet+gaze · GIMO destination error (known scenes) | global translation error: 0.316 -> 0.245 | Improved |
| replace PointNet global scene feature with PointNet++ per-point features (ablation) | Ours · GIMO new scenes | error | Improved |
| use cross-modal transformer instead of vanilla transformer (ablation) | Ours · GIMO path error (new scenes) | path error | Improved |
Closest papers by meaning
- Multimodal Sense-Informed Forecasting of 3D Human Motions (CVPR 2024 · similarity 0.87)
- EyEar: Learning Audio Synchronized Human Gaze Trajectory Based on Physics-Informed Dynamics (AAAI 2025 · similarity 0.86)
- Vision-Guided Action: Enhancing 3D Human Motion Prediction with Gaze-informed Affordance in 3D Scenes (CVPR 2025 · similarity 0.86)
- GazeFlow: From Human Gaze Behavior to Generative Egocentric Gaze Prediction (NeurIPS 2026 · similarity 0.85)
- Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span (NeurIPS 2025 · similarity 0.85)
- SimpliHuMoN: Simplifying Human Motion Prediction (NeurIPS 2026 · 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.
