Research map / Vision-language and multimodal / Cross-modal learning
Show Your Faith: Cross-Modal Confidence-Aware Network for Image-Text Matching
Huatian Zhang, Zhendong Mao, Kun Zhang, Yongdong Zhang
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 cross-modal confidence-aware relevance scoring | CMCAN · Flickr30K | Text retrieval R@1: 77.8 -> 79.5 | Improved |
| Use cross-modal confidence-aware relevance scoring | CMCAN · Flickr30K | R@sum: 499.6 -> 507.8 | Improved |
| Use cross-modal confidence-aware relevance scoring | CMCAN · MSCOCO 1K | Text retrieval R@1: 79.6 -> 81.2 | Improved |
| Use cross-modal confidence-aware relevance scoring | CMCAN · MSCOCO 1K | R@sum: 524.3 -> 529.3 | Improved |
| Use cross-modal confidence-aware relevance scoring | CMCAN · MSCOCO 5K | Text retrieval R@1: 57.8 -> 61.5 | Improved |
| Use cross-modal confidence-aware relevance scoring | CMCAN · MSCOCO 5K | Image retrieval R@1: 41.9 -> 44.0 | Improved |
| Add matching confidence weighting to local region-queried similarities (ablation) | CMCAN relevance measurement · Flickr30K | Text retrieval R@1: 75.9 -> 77.5 | Improved |
| Add matching confidence weighting to local region-queried similarities (ablation) | CMCAN relevance measurement · Flickr30K | Image retrieval R@10: 86.6 -> 88.9 | Improved |
| Add matching confidence weighting to local region-queried similarities (ablation) | CMCAN relevance measurement · Flickr30K | R@sum: 494.0 -> 499.3 | Improved |
Closest papers by meaning
- Identification of Necessary Semantic Undertakers in the Causal View for Image-Text Matching (AAAI 2024 · similarity 0.90)
- Fine-Grained Image-Text Matching by Cross-Modal Hard Aligning Network (CVPR 2023 · similarity 0.90)
- Stacked Cross Attention for Image-Text Matching (ECCV 2018 · similarity 0.89)
- Image-Text Embedding Learning via Visual and Textual Semantic Reasoning (TPAMI 2022 · similarity 0.89)
- Text as Partial Constraint: Core–Residual Alignment for Robust Vision–Language Learning (NeurIPS 2026 · similarity 0.87)
- Noise-Aware Image Captioning with Progressively Exploring Mismatched Words (AAAI 2024 · 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.
