Research map / Vision-language and multimodal / Human and embodied modeling
Learning from Human Gaze: Human-like Robot Social Navigation in Dense Crowds
Zhecheng Yu, Yan Lyu, Chen Yang, Tao Chen, Yishuang Zhang, Bo Ling, Peng Wang, Guanyu Gao, Weiwei Wu, Brian Y. Lim
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-based saliency filtering over all pedestrian masks (ablation) | Gaze2Nav · GazeNav test | ADE: 0.2861 -> 0.2541 | Improved |
| add semantic saliency matching instead of raw gaze heatmaps (ablation) | Gaze2Nav · GazeNav test | ADE: 0.2946 -> 0.2541 | Improved |
| add gaze regularization loss in Motion Planner (ablation) | Gaze2Nav · GazeNav test | ADE: 0.2768 -> 0.2541 | Improved |
| add motion regularization loss in Gaze Predictor (ablation) | Gaze2Nav · GazeNav test | Gaze MAE: 5.969 -> 3.876 | Improved |
| add motion regularization loss in Gaze Predictor (ablation) | Gaze2Nav · GazeNav test | ADE: 0.2653 -> 0.2541 | Improved |
| predict gaze point first then match pedestrians, vs direct mask prediction (ablation) | Gaze2Nav · GazeNav test | Saliency F1: 0.5739 -> 0.8755 | Improved |
| add Gaze2Nav gaze pipeline vs best gaze baseline | ViNT+CGL · GazeNav test | ADE: 0.3005 -> 0.2541 | Improved |
| add CGL gaze alignment loss | ViNT · GazeNav test | ADE: 0.3160 -> 0.3005 | Improved |
| add Foveated gaze blurring | GNM · GazeNav test | ADE: 0.4139 -> 0.3850 | Improved |
| Gaze2Nav vs ViNT in Overtaking scenario | ViNT · GazeNav test, Overtaking | ADE: 0.3750 -> 0.2908 | Improved |
| Gaze2Nav vs ViNT in Following scenario | ViNT · GazeNav test, Following | ADE: 0.2608 -> 0.2289 | Improved |
Closest papers by meaning
- MTGS: A Novel Framework for Multi-Person Temporal Gaze Following and Social Gaze Prediction (NeurIPS 2024 · similarity 0.88)
- Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models (NeurIPS 2026 · similarity 0.86)
- Sharingan: A Transformer Architecture for Multi-Person Gaze Following (CVPR 2024 · similarity 0.86)
- EyEar: Learning Audio Synchronized Human Gaze Trajectory Based on Physics-Informed Dynamics (AAAI 2025 · similarity 0.86)
- GazeFlow: From Human Gaze Behavior to Generative Egocentric Gaze Prediction (NeurIPS 2026 · similarity 0.86)
- ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling (NeurIPS 2026 · similarity 0.86)
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.
