Research map / 3D vision / 3D generation
ChildPlay: A New Benchmark for Understanding Children's Gaze Behaviour
Samy Tafasca, Anshul Gupta, Jean-Marc Odobez
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 |
|---|---|---|---|
| replace 2D gaze cone with explicit 3D field-of-view heatmap from geometry-preserving point cloud (ablation) | gaze target model · ChildPlay full data (not fine-tuned) | Dist: 0.127 -> 0.115 | Improved |
| replace 2D gaze cone with 3DFoV (ablation) | gaze target model · GazeFollow | AUC / P.Head: AUC 0.939 -> 0.936 | No clear effect |
| replace 2D gaze cone with 3DFoV after fine-tuning (ablation) | gaze target model · ChildPlay full data (fine-tuned) | Dist: 0.121 -> 0.107 | Improved |
| fine-tune on ChildPlay children data | gaze target model · ChildPlay children | P.Head: 0.509 -> 0.604 | Improved |
| fine-tune on ChildPlay for adults | gaze target model · ChildPlay adults | P.Head: 0.681 -> 0.704 | Improved |
| evaluate on children versus adults | gaze target model · ChildPlay | P.Head vs Dist: children Dist 0.098 vs adults 0.121; P.Head 18.7% lower for children | Mixed |
| 3DFoV model compared to Gupta et al. after fine-tuning on ChildPlay | gaze target model · ChildPlay full data | P.Head: 0.694 (Gupta) vs 0.663 | Hurt |
| add 3DFoV model versus Jin et al. on VAT and GazeFollow distance | gaze target model · VideoAttentionTarget | Dist: 0.109 vs 0.109 | No clear effect |
Closest papers by meaning
- Toward Semantic Gaze Target Detection (NeurIPS 2024 · similarity 0.87)
- Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models (NeurIPS 2026 · similarity 0.85)
- MTGS: A Novel Framework for Multi-Person Temporal Gaze Following and Social Gaze Prediction (NeurIPS 2024 · similarity 0.84)
- EyEar: Learning Audio Synchronized Human Gaze Trajectory Based on Physics-Informed Dynamics (AAAI 2025 · similarity 0.84)
- ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling (NeurIPS 2026 · similarity 0.84)
- BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models (CVPR 2026 · 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.
