Research map / Vision-language and multimodal / Cross-modal learning
Sample Weighted Incomplete Multimodal Clustering Based on Graph Coarsening Label Extraction
Zhenjiao Liu, Xue Xiao, Yao Chen, Jiao Xue, Shubin Ma, Liang Zhao
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 |
|---|---|---|---|
| use IMC-GCSW instead of HCP-IMSC | IMC-GCSW · Caltech101-7 (90% incomplete) | ACC: 55.29 -> 57.78 | Improved |
| use IMC-GCSW instead of HCP-IMSC | IMC-GCSW · Caltech101-7 (90% incomplete) | runtime (s): 236.79 -> 160.57 | Improved |
| use IMC-GCSW instead of HCP-IMSC | IMC-GCSW · Citrus Pest Dataset | ACC: 73.89 -> 82.74 | Improved |
| use IMC-GCSW instead of UGCF | IMC-GCSW · Citrus Disease Dataset | ACC: 52.82 -> 62.32 | Improved |
| use IMC-GCSW instead of HCP-IMSC | IMC-GCSW · Citrus Disease Dataset | F-score: 54.83 -> 67.24 | Improved |
| raise the missing rate from 0.1 to 0.9 | IMC-GCSW · ORL | ACC: 83.07 -> 16.54 | Hurt |
| compare IMC-GCSW with deep method Mask-IMVC at missing rate 0.9 | IMC-GCSW · ORL | ACC: 16.54 vs 39.61 | Hurt |
| compare IMC-GCSW with deep method Mask-IMVC at missing rate 0.1 | IMC-GCSW · ORL | ACC: 57.78 -> 83.07 | Improved |
| use IMC-GCSW instead of HCP-IMSC at missing rate 0.5 | IMC-GCSW · Yale | ACC: 33.27 -> 37.33 | Improved |
| compare IMC-GCSW with deep method IMC-MCL at missing rate 0.5 | IMC-GCSW · Yale | ACC: 45.94 vs 37.33 | Hurt |
| compare IMC-GCSW with Mask-IMVC at missing rate 0.1 | IMC-GCSW · Statlog | ACC: 56.46 vs 47.63 | Hurt |
Closest papers by meaning
- Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning (CVPR 2025 · similarity 0.87)
- A Peer-review Look on Multi-modal Clustering: An Information Bottleneck Realization Method (ICML 2025 · similarity 0.86)
- Graph4MM: Weaving Multimodal Learning with Structural Information (ICML 2025 · similarity 0.85)
- Super Deep Contrastive Information Bottleneck for Multi-modal Clustering (ICML 2025 · similarity 0.85)
- Incomplete and Unpaired Multi-View Graph Clustering with Cross-View Feature Fusion (AAAI 2025 · similarity 0.84)
- Semi-Supervised Multimodal Classification Through Learning from Modal and Strategic Complementarities (AAAI 2025 · 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.
