Research map / Vision-language and multimodal / Cross-modal learning
Harmonized Multimodal Learning with Gaussian Process Latent Variable Models
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 prior (trace) (ablation) | mGPLVM · PASCAL cross-modal retrieval | mAP (average): 0.1413 -> 0.1732 | Improved |
| add harmonization prior (F-norm) (ablation) | mGPLVM · PASCAL cross-modal retrieval | mAP (average): 0.1413 -> 0.1613 | Improved |
| add harmonization prior (trace) (ablation) | m-SimGP · PASCAL cross-modal retrieval | mAP (average): 0.2839 -> 0.3281 | Improved |
| add harmonization prior (trace) (ablation) | m-RSimGP · PASCAL cross-modal retrieval | mAP (average): 0.3288 -> 0.3830 | Improved |
| add harmonization prior (trace) (ablation) | mGPLVM · Wiki cross-modal retrieval | mAP (average): 0.1841 -> 0.2229 | Improved |
| add harmonization prior (l2,1-norm) (ablation) | m-SimGP · Wiki cross-modal retrieval | mAP (average): 0.4262 -> 0.4616 | Improved |
| add harmonization prior (trace) (ablation) | m-RSimGP · Wiki cross-modal retrieval | mAP (average): 0.4558 -> 0.5102 | Improved |
| add harmonization prior (trace) (ablation) | mGPLVM · TVGraz cross-modal retrieval | mAP (average): 0.2715 -> 0.3545 | Improved |
| add harmonization prior (trace) (ablation) | m-RSimGP · TVGraz cross-modal retrieval | mAP (average): 0.5091 -> 0.5556 | Improved |
| add harmonization prior (trace) (ablation) | mGPLVM · MSCOCO cross-modal retrieval | mAP (average): 0.5631 -> 0.6272 | Improved |
| add harmonization prior (trace) (ablation) | m-RSimGP · MSCOCO cross-modal retrieval | mAP (average): 0.6555 -> 0.6682 | Improved |
| use trace instead of F-norm harmonization function (ablation) | hm-RSimGP · PASCAL cross-modal retrieval | mAP (average): 0.3526 -> 0.3830 | Improved |
Closest papers by meaning
- Multimodal Gaussian Process Latent Variable Models With Harmonization (ICCV 2017 · similarity 0.97)
- Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process (NeurIPS 2025 · similarity 0.89)
- Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning (NeurIPS 2025 · similarity 0.88)
- MSP: Modality Self-Play for Training Multimodal LLMs Without Paired Cross-Modal Data (NeurIPS 2026 · similarity 0.87)
- On the Value of Cross-Modal Misalignment in Multimodal Representation Learning (NeurIPS 2025 · similarity 0.87)
- CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning (NeurIPS 2025 · 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.
