Research map / Vision-language and multimodal / Human and embodied modeling
Toddler-Inspired Visual Object Learning
Sven Bambach, David Crandall, Linda Smith, Chen Yu
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 |
|---|---|---|---|
| train on toddler egocentric data instead of parent egocentric data | VGG16 (ImageNet-pretrained) · clean 24-toy test set | classification accuracy | Improved |
| train on large attended objects instead of small ones (ablation) | VGG16 on toddler data · clean 24-toy test set | classification accuracy | Improved |
| train on diverse subset instead of similar subset (ablation) | VGG16 on toddler data · clean 24-toy test set | classification accuracy | Improved |
| use original toddler distribution (mix of similar and diverse) instead of diverse-only or similar-only subsets (ablation) | VGG16 on toddler data · clean 24-toy test set | classification accuracy | Improved |
| remove foveated blurring (ablation) | VGG16 on egocentric data · clean 24-toy test set | classification accuracy | Mixed |
Closest papers by meaning
- Learning from an Infant’s Visual Experience (AAAI 2024 · similarity 0.88)
- Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learning (CVPR 2025 · similarity 0.88)
- Object Concepts Emerge from Motion (NeurIPS 2025 · similarity 0.87)
- BabyVLM-V2: Toward Developmentally Grounded Pretraining and Benchmarking of Vision Foundation Models (CVPR 2026 · similarity 0.87)
- Alignment of CNN and Human Judgments of Geometric and Topological Concepts (AAAI 2025 · similarity 0.86)
- BabyVision: Visual Reasoning Beyond Language (ICML 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.
