Research map / Label-efficient and robust learning / Recognition and long-tail
Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification
Renchun You, Zhiyao Guo, Lei Cui, Xiang Long, Yingze Bao, Shilei Wen
Read the paperCheck 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 |
|---|---|---|---|
| Add CMA to ResNet-101 (ablation) | ResNet-101 · MS-COCO | mAP: 79.9 -> 83.4 | Improved |
| Replace general self-attention with CMA (ablation) | MS-COCO classifier · MS-COCO | mAP: 81.1 -> 83.4 | Improved |
| Use multi-scale CMA instead of single-scale CMA (ablation) | CMA · MS-COCO | mAP: 83.4 -> 83.8 | Improved |
| Replace Word2vec label embeddings with ASGE (ablation) | MS-CMA · MS-COCO | mAP: 82.5 -> 83.8 | Improved |
| Use CMA instead of self-attention | SNet video classifier · YouTube-8M Segments | mAP: 53.2 -> 55.8 | Improved |
| Use CMA instead of self-attention | FC video classifier · YouTube-8M Segments | mAP: 49.6 -> 50.7 | Improved |
| Use SNet instead of FC with CMA (ablation) | CMA video classifier · YouTube-8M Segments | mAP: 50.7 -> 55.8 | Improved |
| Use multi-scale CMA instead of single-scale CMA | CMA · NUS-WIDE | mAP: 60.8 -> 61.4 | Improved |
Closest papers by meaning
- Multilabel Deep Visual-Semantic Embedding (TPAMI 2019 · similarity 0.89)
- Language-Driven Cross-Modal Classifier for Zero-Shot Multi-Label Image Recognition (ICML 2024 · similarity 0.87)
- Incomplete Multi-View Multi-label Learning via Disentangled Representation and Label Semantic Embedding (CVPR 2025 · similarity 0.87)
- Multi-View Multi-Label Classification via View-Label Matching Selection (AAAI 2025 · similarity 0.87)
- Attention-Induced Embedding Imputation for Incomplete Multi-View Partial Multi-Label Classification (AAAI 2024 · similarity 0.87)
- Partial Multi-View Multi-Label Classification via Semantic Invariance Learning and Prototype Modeling (ICML 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.
