Research map / Learning theory and algorithms / Prediction and decision losses
Order-Preserving Dimension Reduction for Multimodal Semantic Embedding
Chengyu Gong, Gefei Shen, Luanzheng Guo, Nathan R. Tallent, Dongfang 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 PCA instead of MDS as the dimension-reduction method (ablation) | OPDR · Materials Project datasets | neighborhood preservation accuracy: PCA peak accuracy of 100%, above MDS | Improved |
| use PCA instead of MDS on Flickr30k and OmniCorpus (ablation) | OPDR · Flickr30k and OmniCorpus | neighborhood preservation accuracy | Improved |
| swap embedding model among BERT, ViT and CLIP (ablation) | OPDR · Observable materials, Flickr30k, OmniCorpus | neighborhood preservation accuracy | No clear effect |
| increase target dimension n toward sample count m (ablation) | OPDR with PCA · six multimodal datasets | neighborhood preservation accuracy | Improved |
Closest papers by meaning
- Your Embedding Model Is SMARTer Than You Think (NeurIPS 2026 · similarity 0.86)
- VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks (ICLR 2025 · similarity 0.85)
- MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction (ICLR 2026 · similarity 0.84)
- U-MARVEL: Unveiling Key Factors for Universal Multimodal Retrieval via Embedding Learning with MLLMs (ICLR 2026 · similarity 0.84)
- Aligning Multimodal Representations through an Information Bottleneck (ICML 2025 · similarity 0.84)
- Learning Shared Representations from Unpaired Data (NeurIPS 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.
