Research map / Label-efficient and robust learning / Recognition and long-tail
Joint Multi-View Representation Learning and Image Tagging
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 |
|---|---|---|---|
| replace equal-weight multi-view structure term with softmax over most-disagreeing view (ablation) | OPSL · Corel5k | F1: 42.1 -> 43.3 | Helped |
| replace equal-weight multi-view structure term with softmax over most-disagreeing view (ablation) | OPSL · ESP Game | F1: 32.8 -> 33.9 | Helped |
| replace equal-weight multi-view structure term with softmax over most-disagreeing view (ablation) | OPSL · NUS-WIDE | F1: 37.2 -> 38.4 | Helped |
| softmax view weighting (OPSL vs OPSL-V) (ablation) | OPSL · Corel5k | MAP: 28.8 -> 29.6 | Helped |
| softmax view weighting (OPSL vs OPSL-V) (ablation) | OPSL · ESP Game | MAP: 15.3 -> 16.1 | Helped |
| joint subspace and SVM learning (OPSL) instead of best baseline OGL | image tagging · ESP Game | MAP: 17.0 -> 16.1 | Hurt |
| OPSL vs best baseline (NMF-KNN) | image tagging · Corel5k | F1: 41.0 -> 43.3 | Helped |
| increase semantic embedding weight eta to 10 or more (ablation) | OPSL · Corel5k | annotation performance | Hurt |
| subspace dimension r below 200 (ablation) | OPSL · Corel5k | annotation performance | Hurt |
Closest papers by meaning
- Diverse Image Annotation (CVPR 2017 · similarity 0.89)
- Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets (CVPR 2021 · similarity 0.86)
- Fast Zero-Shot Image Tagging (CVPR 2016 · similarity 0.86)
- Tag2Text: Guiding Vision-Language Model via Image Tagging (ICLR 2024 · similarity 0.84)
- MOFI: Learning Image Representations from Noisy Entity Annotated Images (ICLR 2024 · similarity 0.83)
- Doomed to Re-Annotate, Forever: The ImageNet Story (NeurIPS 2026 · similarity 0.82)
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.