Research map / Vision-language and multimodal / Human and embodied modeling
Text-Guided Attention Model for Image Captioning
Read the paperCheck 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 text-guided attention and use top-k consensus captions rather than uniform attention (ablation) | Image captioning model with ResNet · MS-COCO test split | CIDEr: 0.996 -> 1.024 | Helped |
| add text-guided attention and use top-k consensus captions rather than uniform attention (ablation) | Image captioning model with ResNet · MS-COCO test split | BLEU-4: 0.319 -> 0.326 | Helped |
| use top-k consensus guidance captions instead of a single highest-consensus caption (ablation) | Text-guided attention model with ResNet · MS-COCO test split | CIDEr: 1.010 -> 1.024 | Helped |
| use top-k consensus guidance captions instead of a single highest-consensus caption (ablation) | Text-guided attention model with ResNet · MS-COCO test split | BLEU-4: 0.323 -> 0.326 | Helped |
| use top-k consensus guidance captions instead of a single highest-consensus caption (ablation) | Text-guided attention model with VGG-FCN · MS-COCO test split | CIDEr: 0.972 -> 0.982 | Helped |
| use top-k consensus guidance captions instead of a single highest-consensus caption (ablation) | Text-guided attention model with VGG-FCN · MS-COCO test split | BLEU-4: 0.313 -> 0.316 | Helped |
| replace VGG-FCN with ResNet as the image encoder (ablation) | Ours-ATT-kCC · MS-COCO test split | CIDEr: 0.982 -> 1.024 | Helped |
Closest papers by meaning
- Image Captioning With Semantic Attention (CVPR 2016 · similarity 0.90)
- Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning (CVPR 2017 · similarity 0.90)
- Attention Correctness in Neural Image Captioning (AAAI 2017 · similarity 0.89)
- Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models (ICML 2025 · similarity 0.89)
- Patch Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception (CVPR 2025 · similarity 0.88)
- Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning (ICLR 2025 · similarity 0.87)
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.