Research map / Detection and segmentation / CNN features
Does Text Attract Attention on E-Commerce Images: A Novel Saliency Prediction Dataset and Method
Lai Jiang, Yifei Li, Shengxi Li, Mai Xu, Se Lei, Yichen Guo, Bo Huang
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 |
|---|---|---|---|
| Use the complete SSwin-Transformer, saliency/text heads, and information flow | Saliency prediction on SalECI · SalECI test | CC: 0.605±0.148 -> 0.687±0.175 | Improved |
| Use the complete SSwin-Transformer, saliency/text heads, and information flow | Saliency prediction on SalECI · SalECI test | KL: 0.768±0.262 -> 0.652±0.478 | Improved |
| Use the complete SSwin-Transformer, saliency/text heads, and information flow | Saliency prediction on SalECI · SalECI test | sAUC: 0.811± 0.058 -> 0.783±0.064 | Hurt |
| Add the attention loss (ablation) | SSwin-Transformer and saliency head · SalECI test | CC: 0.629 -> 0.670 | Improved |
| Add the text head (ablation) | SSwin-Transformer and saliency head · SalECI test | CC: 0.629 -> 0.633 | Improved |
| Add the information flow (ablation) | SSwin-Transformer, saliency head, attention loss, and text head · SalECI test | CC: 0.678 -> 0.687 | Improved |
| Add the attention loss (ablation) | SSwin-Transformer, saliency head, text head, and information flow · SalECI test | AUC: 0.863 -> 0.868 | Improved |
Closest papers by meaning
- Task-driven Webpage Saliency (ECCV 2018 · similarity 0.86)
- Image Search With Text Feedback by Visiolinguistic Attention Learning (CVPR 2020 · similarity 0.84)
- Learning From Unique Perspectives: User-Aware Saliency Modeling (CVPR 2023 · similarity 0.84)
- TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval (NeurIPS 2026 · similarity 0.83)
- STAIR: Manipulating Collaborative and Multimodal Information for E-Commerce Recommendation (AAAI 2025 · similarity 0.81)
- Transformer-Empowered Multi-Modal Item Embedding for Enhanced Image Search in E-commerce (AAAI 2024 · similarity 0.81)
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.
