Research map / Label-efficient and robust learning / Recognition and long-tail
Beyond Shared Subspace: A View-Specific Fusion for Multi-View Multi-Label Learning
Read the paperCheck 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 |
|---|---|---|---|
| Use view-specific graph fusion instead of shared-subspace MVML methods | D-VSM · Emotions, Scene, Corel5k, Pascal, Iaprtc12, Espgame, Mirflickr | Average Precision: 0.764±0.027 -> 0.835±0.027; 0.852±0.012 -> 0.890±0.011; 0.430±0.007 -> 0.475±0.008; 0.721±0.003 -> 0.767±0.003; 0.348±0. | Helped |
| Add intra-view correlations (ablation) | D-VSM · Emotions, Corel5k, Mirflickr | Micro-F1: 0.687±0.025 -> 0.700±0.034; 0.322±0.020 -> 0.399±0.004; 0.052±0.002 -> 0.055±0.002 | Helped |
| Add inter-view alignments (ablation) | D-VSM · Emotions, Corel5k, Mirflickr | Micro-F1: 0.698±0.026 -> 0.700±0.034; 0.357±0.010 -> 0.399±0.004; 0.049±0.002 -> 0.055±0.002 | Helped |
| Add both intra-view correlations and inter-view alignments (ablation) | D-VSM · Emotions, Corel5k, Mirflickr | Micro-F1: 0.661±0.046 -> 0.700±0.034; 0.220±0.021 -> 0.399±0.004; 0.045±0.003 -> 0.055±0.002 | Helped |
| Increase the number of intra-view neighbors k (ablation) | D-VSM · Emotions, Corel5k, Mirflickr | multiple evaluation metrics | Mixed |
Closest papers by meaning
- Multi-View Multi-Label Classification via View-Label Matching Selection (AAAI 2025 · similarity 0.91)
- Partial Multi-View Multi-Label Classification via Semantic Invariance Learning and Prototype Modeling (ICML 2024 · similarity 0.90)
- Incomplete Multi-View Multi-label Learning via Disentangled Representation and Label Semantic Embedding (CVPR 2025 · similarity 0.89)
- Tensorized Multi-View Multi-Label Classification via Laplace Tensor Rank (ICML 2025 · similarity 0.89)
- Theory-Inspired Deep Multi-View Multi-Label Learning with Incomplete Views and Noisy Labels (CVPR 2025 · similarity 0.89)
- Uncertainty-Aware Global-View Reconstruction for Multi-View Multi-Label Feature Selection (AAAI 2025 · similarity 0.88)
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.