Research map / Vision-language and multimodal / Cross-modal learning
AMC: Attention guided Multi-modal Correlation Learning for Image Search
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 |
|---|---|---|---|
| apply query-guided intra-attention to the image modality (ablation) | DSSM-Img · Clickture dev | NDCG@5: 0.6005 -> 0.6168 | Helped |
| apply query-guided intra-attention to the keyword modality (ablation) | DSSM-Key · Clickture dev | NDCG@5: 0.5715 -> 0.5960 | Helped |
| combine the visual and keyword attention representations with late fusion (ablation) | Clickture image search · Clickture dev | NDCG@5: 0.6168 -> 0.6232 | Helped |
| use query-conditioned inter-attention instead of late fusion (ablation) | AMC image search · Clickture dev | NDCG@5: 0.6232 -> 0.6325 | Helped |
| apply query-guided intra-attention to the keyword modality (ablation) | DSSM-Key · Adobe Stock Dataset test | R@10: 0.4207 -> 0.4322 | Helped |
| apply query-guided intra-attention to the visual modality (ablation) | DSSM-Img · Adobe Stock Dataset test | R@10: 0.4025 -> 0.4049 | No clear effect |
| combine visual and keyword attention representations with late fusion (ablation) | Adobe Stock image search · Adobe Stock Dataset test | R@10: 0.4322 -> 0.4620 | Helped |
| use query-conditioned inter-attention instead of late fusion (ablation) | AMC image search · Adobe Stock Dataset test | R@10: 0.4620 -> 0.4673 | Helped |
| add keyword modality with late fusion (ablation) | Skip-Vgg · CIC test | R@10: 81.5 -> 82.0 | Helped |
| replace late fusion with query-conditioned inter-attention (ablation) | Skip-Vgg-Key-LF · CIC test | R@10: 82.0 -> 83.0 | Helped |
| add keyword modality with late fusion (ablation) | Skip-Res · CIC test | R@10: 86.1 -> 86.5 | Helped |
| replace late fusion with query-conditioned inter-attention (ablation) | Skip-Res-Key-LF · CIC test | R@10: 86.5 -> 87.8 | Helped |
Closest papers by meaning
- Context-Aware Attention Network for Image-Text Retrieval (CVPR 2020 · similarity 0.91)
- Text-Guided Attention Model for Image Captioning (AAAI 2017 · similarity 0.87)
- Hierarchical Attention Network for Image Captioning (AAAI 2019 · similarity 0.87)
- An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval (NeurIPS 2024 · similarity 0.86)
- Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion (ICLR 2025 · similarity 0.84)
- Dynamic Weighted Combiner for Mixed-Modal Image Retrieval (AAAI 2024 · similarity 0.84)
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.