Research map / Vision-language and multimodal / Human and embodied modeling
Canonical Correlation Inference for Mapping Abstract Scenes to Text
Nikos Papasarantopoulos, Helen Jiang, Shay Cohen
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 CCA inference instead of phrase-based SMT | Abstract scene captioning · Abstract Scenes test | BLEU: 43.7 -> 26.1 | Hurt |
| Use CCA inference instead of phrase-based SMT | Abstract scene captioning · Abstract Scenes test | METEOR: 35.6 -> 25.6 | Hurt |
| Use CCA inference instead of phrase-based SMT | Abstract scene captioning · Abstract Scenes test | unique captions: 359 -> 496; an increase of 38.1% | Improved |
| Vary the projection dimension m from 30 to 300 (ablation) | CCA · Abstract Scenes development set | BLEU | No clear effect |
Closest papers by meaning
- Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding (NeurIPS 2026 · similarity 0.85)
- The Scene Language: Representing Scenes with Programs, Words, and Embeddings (CVPR 2025 · similarity 0.85)
- Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition (CVPR 2025 · similarity 0.85)
- Compositional Entailment Learning for Hyperbolic Vision-Language Models (ICLR 2025 · similarity 0.84)
- Causal Graphical Models for Vision-Language Compositional Understanding (ICLR 2025 · similarity 0.84)
- Image as a Language: Revisiting Scene Text Recognition via Balanced, Unified and Synchronized Vision-Language Reasoning Network (AAAI 2024 · 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.
