AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Cross-Linked Unified Embedding for cross-modality representation learning

Xinming Tu, Zhi-Jie Cao, Chen-Rui Xia, Sara Mostafavi, Ge Gao

NeurIPS 2022 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 5 citations (OpenAlex)

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 changedWhereMeasuredEffect
add adversarial modality discriminator loss (ablation)CLUE · NeurIPS 2021 multimodal competition testmatching score Overall: 0.0284 -> 0.0539Improved
add mean squared error alignment loss (ablation)CLUE · NeurIPS 2021 multimodal competition testmatching score Overall: 0.0451 -> 0.0539Improved
add cross-linked loss (cross-encoders) (ablation)CLUE · NeurIPS 2021 multimodal competition testmatching score Overall: 0.0444 -> 0.0539Improved
use all three loss components versus none (ablation)CLUE · NeurIPS 2021 multimodal competition testmatching score Overall: 0.0001 -> 0.0539Improved
CLUE versus CoboltCLUE · Competition data benchmarkmatching score Overall: 0.0244 -> 0.0539Improved
CLUE versus MultiVICLUE · Competition data benchmarkmatching score Overall: 0.0169 -> 0.0539Improved
CLUE versus Bridge-integrationCLUE · Competition data benchmarkmatching score Overall: 0.0116 -> 0.0539Improved
CLUE versus MultiVI (second best)CLUE · SHARE-seqmatching score Overall: 0.0601 -> 0.135Improved
CLUE versus Bridge-integrationCLUE · SHARE-seqmatching score Overall: 0.0335 -> 0.135Improved
CLUE versus Bridge-integration (best baseline)CLUE · Competition data benchmarkFOSCTTM Overall (lower better): 0.0344 -> 0.0162Improved
CLUE versus MultiVICLUE · Competition data benchmarkFOSCTTM Overall (lower better): 0.0635 -> 0.0162Improved
CLUE versus Top2 competition methodCLUE · NeurIPS 2021 multimodal competition testmatching score Overall: 0.0427 -> 0.0539Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy