Research map / Vision-language and multimodal / Human and embodied modeling
Acquiring Common Sense Spatial Knowledge Through Implicit Spatial Templates
Guillem Collell, Luc Van Gool, Marie-Francine Moens
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 GloVe embeddings instead of random embeddings (ablation) | REG · generalized words | R2: 0.438 -> 0.633 | Improved |
| use GloVe embeddings instead of one-hot vectors (ablation) | REG · generalized words | R2: 0.425 -> 0.633 | Improved |
| use GloVe embeddings instead of random embeddings (ablation) | PIX · generalized words | above/below accuracy: 0.644 -> 0.717 | Improved |
| use GloVe embeddings instead of one-hot vectors (ablation) | PIX · generalized triplets | above/below accuracy: 0.738 -> 0.751 | No clear effect |
| use GloVe embeddings instead of random embeddings (ablation) | REG · raw implicit data | R2: 0.693 -> 0.704 | No clear effect |
| use one-hot embeddings instead of GloVe (ablation) | REG · raw implicit data | R2: 0.704 -> 0.720 | No clear effect |
| hold out generalized triplets from training | REG_EMB · generalized triplets | R2: 0.774 -> 0.746 | Hurt |
| hold out generalized words from training | REG_EMB · generalized words | R2: 0.725 -> 0.633 | Hurt |
| hold out generalized words from training | REG_1H · generalized words | R2: 0.740 -> 0.425 | Hurt |
Closest papers by meaning
- Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models (NeurIPS 2024 · similarity 0.88)
- Spatial Understanding from Videos: Structured Prompts Meet Simulation Data (NeurIPS 2025 · similarity 0.88)
- Stitch and Tell: A Structured Data Augmentation Method for Spatial Understanding (NeurIPS 2025 · similarity 0.88)
- EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs (CVPR 2026 · similarity 0.88)
- SpatiaLab: Can Vision–Language Models Perform Spatial Reasoning in the Wild? (ICLR 2026 · similarity 0.88)
- SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models (ICLR 2026 · 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.
