Research map / Graph learning / Knowledge and temporal graphs
Graph Structured Network for Image-Text Matching
Chunxiao Liu, Zhendong Mao, Tianzhu Zhang, Hongtao Xie, Bin Wang, Yongdong Zhang
Check 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 |
|---|---|---|---|
| Combine sparse and dense textual graphs (ablation) | GSMN · Flickr30K | Image-to-Text R@1: 71.4 -> 76.4 | Improved |
| Combine sparse and dense textual graphs (ablation) | GSMN · Flickr30K | Text-to-Image R@1: 53.9 -> 57.4 | Improved |
| Combine sparse and dense textual graphs (ablation) | GSMN · MSCOCO | Image-to-Text R@1: 76.1 -> 78.4 | Improved |
| Combine sparse and dense textual graphs (ablation) | GSMN · MSCOCO | Text-to-Image R@1: 60.4 -> 63.3 | Improved |
| Add graph structure and neighborhood propagation to node-level matching (ablation) | GSMN · Flickr30K | Image-to-Text R@1: 63.2 -> 71.4 | Improved |
| Add graph structure and neighborhood propagation to node-level matching (ablation) | GSMN · Flickr30K | Text-to-Image R@1: 48.7 -> 53.9 | Improved |
| Use two GCN layers instead of one (ablation) | GSMN · Flickr30K | Image-to-Text R@1: 71.4 -> 68.4 | Hurt |
| Use two GCN layers instead of one (ablation) | GSMN · Flickr30K | Text-to-Image R@1: 53.9 -> 51.5 | Hurt |
| Replace Bi-GRU with GRU text encoding (ablation) | GSMN · Flickr30K | Text-to-Image R@1: 53.9 -> 50.9 | Hurt |
| Remove text-to-image matching direction (ablation) | GSMN · Flickr30K | Text-to-Image R@1: 53.9 -> 45.8 | Hurt |
| Remove image-to-text matching direction (ablation) | GSMN · Flickr30K | Image-to-Text R@1: 71.4 -> 67.0 | Hurt |
| Use dense rather than sparse textual graph alone (ablation) | GSMN · MSCOCO | Image-to-Text R@1: 76.1 -> 74.7 | Hurt |
Closest papers by meaning
- Composing Object Relations and Attributes for Image-Text Matching (CVPR 2024 · similarity 0.89)
- Grounded Image Text Matching with Mismatched Relation Reasoning (ICCV 2023 · similarity 0.88)
- Structured Set Matching Networks for One-Shot Part Labeling (CVPR 2018 · similarity 0.88)
- Expressing Objects Just Like Words: Recurrent Visual Embedding for Image-Text Matching (AAAI 2020 · similarity 0.87)
- Learning Two-Branch Neural Networks for Image-Text Matching Tasks (TPAMI 2018 · similarity 0.87)
- MGNet: Learning Correspondences via Multiple Graphs (AAAI 2024 · 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.
