Research map / Vision-language and multimodal / Cross-modal learning
Context-Aware Attention Network for Image-Text Retrieval
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 |
|---|---|---|---|
| Use CAAN instead of BFAN-single | Image-text retrieval · MS-COCO 5-fold 1K test images, sentence retrieval | R@1: 73.7 -> 75.5 | Helped |
| Use CAAN instead of BFAN-single | Image-text retrieval · MS-COCO 5-fold 1K test images, image retrieval | R@1: 58.3 -> 61.3 | Helped |
| Use CAAN instead of SCAN-single | Image-text retrieval · Flickr30K 1K test images, sentence retrieval | R@1: 67.9 -> 70.1 | Helped |
| Use CAAN instead of CAMP | Image-text retrieval · Flickr30K 1K test images, image retrieval | R@1: 51.5 -> 52.8 | Helped |
| Use CAAN instead of CAMP | Image-text retrieval · MS-COCO 5K test images, sentence retrieval | R@1: 50.1 -> 52.5 | Helped |
| Use CAAN instead of CAMP | Image-text retrieval · MS-COCO 5K test images, image retrieval | R@1: 39.0 -> 41.2 | Helped |
| Add inter-modal attention to the average-feature baseline (ablation) | Image-text retrieval · Flickr30K test set, image query | R@1: 58.1 -> 60.6 | Helped |
| Add inter-modal attention to the average-feature baseline (ablation) | Image-text retrieval · Flickr30K test set, sentence query | R@1: 42.0 -> 45.2 | Helped |
| Add feature-based intra-modal attention to the average-feature baseline (ablation) | Image-text retrieval · Flickr30K test set, image query | R@1: 58.1 -> 62.3 | Helped |
| Replace feature-based intra-modal attention with semantics-based attention (ablation) | Image-text retrieval baseline with intra-modal attention · Flickr30K test set, image query | R@1: 62.3 -> 64.5 | Helped |
| Combine inter-modal attention with feature-based intra-modal attention (ablation) | Image-text retrieval · Flickr30K test set, image query | R@1: 62.3 -> 62.6 | Hurt |
| Combine inter-modal attention with semantics-based intra-modal attention (ablation) | Image-text retrieval · Flickr30K test set, image query | R@1: 64.5 -> 70.1 | Helped |
Closest papers by meaning
- AMC: Attention guided Multi-modal Correlation Learning for Image Search (CVPR 2017 · similarity 0.91)
- Fine-Grained Image-Text Matching by Cross-Modal Hard Aligning Network (CVPR 2023 · similarity 0.89)
- Multi-Modality Cross Attention Network for Image and Sentence Matching (CVPR 2020 · similarity 0.88)
- An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval (NeurIPS 2024 · similarity 0.88)
- Text Embedding is Not All You Need: Attention Control for Text-to-Image Semantic Alignment with Text Self-Attention Maps (CVPR 2025 · similarity 0.87)
- Adaptive Prompt-Based Semantic Embedding with Inspire Potential of Implicit Knowledge for Cross-Modal Retrieval (AAAI 2025 · 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.