Research map / Vision-language and multimodal / Cross-modal learning
Multimodal Gaussian Process Latent Variable Models With Harmonization
Guoli Song, Shuhui Wang, Qingming Huang, Qi Tian
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 harmonization constraint | mGPLVM · PASCAL Sentence cross-modal retrieval | mAP (average): 0.1413 -> 0.1613 | Improved |
| add harmonization constraint | m-SimGP · PASCAL Sentence cross-modal retrieval | mAP (average): 0.2743 -> 0.3034 | Improved |
| add harmonization constraint | m-RSimGP · PASCAL Sentence cross-modal retrieval | mAP (average): 0.3288 -> 0.3526 | Improved |
| add harmonization constraint | mGPLVM · Wikipedia cross-modal retrieval | mAP (average): 0.1841 -> 0.2109 | Improved |
| add harmonization constraint | m-SimGP · Wikipedia cross-modal retrieval | mAP (average): 0.4262 -> 0.4474 | Improved |
| add harmonization constraint | m-RSimGP · Wikipedia cross-modal retrieval | mAP (average): 0.4558 -> 0.4826 | Improved |
| add harmonization constraint | mGPLVM · TVGraz cross-modal retrieval | mAP (average): 0.2715 -> 0.3400 | Improved |
| add harmonization constraint | m-SimGP · TVGraz cross-modal retrieval | mAP (average): 0.4460 -> 0.4640 | Improved |
| add harmonization constraint | m-RSimGP · TVGraz cross-modal retrieval | mAP (average): 0.5091 -> 0.5393 | Improved |
| add harmonization constraint | mGPLVM · PASCAL kernel vs latent similarity mismatch | Frobenius norm of K - Sx: 277.966 -> 91.683 | Improved |
| increase harmonization weight mu above about 1 | hmGPLVM and hm-SimGP · PASCAL, Wiki, TVGraz | mAP: best around 1 | Hurt |
Closest papers by meaning
- Harmonized Multimodal Learning with Gaussian Process Latent Variable Models (TPAMI 2019 · similarity 0.97)
- Joint Feature Selection and Subspace Learning for Cross-Modal Retrieval (TPAMI 2016 · similarity 0.87)
- Multi-View Oriented GPLVM: Expressiveness and Efficiency (NeurIPS 2025 · similarity 0.86)
- Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process (NeurIPS 2025 · similarity 0.85)
- Generalized Contrastive Learning for Universal Multimodal Retrieval (NeurIPS 2025 · similarity 0.85)
- Cross-Modal Alignment via Variational Copula Modelling (ICML 2025 · similarity 0.85)
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.
