Research map / Vision-language and multimodal / Human and embodied modeling
Comprehending and Ordering Semantics for Image Captioning
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 cross-modal retrieval to mine primary semantic cues (ablation) | Base Transformer captioner with CLIP grid features · COCO Karpathy test split | CIDEr: 123.6 -> 124.9 | Helped |
| Add filtering of irrelevant semantics (ablation) | Base+CR · COCO Karpathy test split | CIDEr: 124.9 -> 125.8 | Helped |
| Add inference of missing relevant semantics (ablation) | Base+CR+FIS · COCO Karpathy test split | CIDEr: 125.8 -> 126.1 | Helped |
| Add semantic ranking of the refined words (ablation) | Base+CR+FIS+IMS · COCO Karpathy test split | CIDEr: 126.1 -> 127.4 | Helped |
| Use COS-Net instead of X-Transformer† | Single-model captioning with CLIP ResNet-101 features · COCO Karpathy test split | CIDEr: 137.2 -> 141.1 | Helped |
| Use COS-Net instead of Transformer† | Image captioning · COCO robust split | CHAIRi: 5.1 -> 3.9 | Helped |
Closest papers by meaning
- Learning Semantic Concepts and Order for Image and Sentence Matching (CVPR 2018 · similarity 0.90)
- Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations (NeurIPS 2019 · similarity 0.88)
- Image Captioning With Semantic Attention (CVPR 2016 · similarity 0.88)
- Captioning Images With Diverse Objects (CVPR 2017 · similarity 0.87)
- Semantic-Conditional Diffusion Networks for Image Captioning (CVPR 2023 · similarity 0.87)
- Top-Down Semantic Refinement for Image Captioning (AAAI 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.