AI Paper Atlas

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

Principled Multimodal Representation Learning

Xiaohao Liu, Xiaobo Xia, See Kiong Ng, Tat‐Seng Chua

TPAMI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities

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 instance-wise regularization on leading eigenvectors (ablation)PMRL · MSR-VTT text-to-video (zero-shot)Recall@1: 53.7 -> 54.5Improved
add instance-wise regularization on leading eigenvectors (ablation)PMRL · DiDeMo text-to-video (zero-shot)Recall@1: 50.2 -> 50.6Improved
add instance-wise regularization on leading eigenvectors (ablation)PMRL · ActivityNet text-to-video (zero-shot)Recall@1: 53.6 -> 56.0Improved
add instance-wise regularization on leading eigenvectors (ablation)PMRL · VATEX text-to-video (zero-shot)Recall@1: 80.0 -> 80.5Improved
add instance-wise regularization to GRAM-style volume loss (ablation)GRAM · ActivityNet text-to-video (zero-shot)Recall@1: 20.1 -> 54.5Improved
optimize only the top singular value instead of top-2 (sigma1+sigma2) (ablation)PMRL · VATEX text-to-video (zero-shot)Recall@1: 79.6 -> 80.5Improved
optimize only the top singular value instead of top-2 (sigma1+sigma2) (ablation)PMRL · AudioCaps text-to-audioRecall@1: 34.8 -> 36.1Improved
optimize only the top singular value instead of top-2 (sigma1+sigma2) (ablation)PMRL · AudioCaps audio-to-textRecall@1: 33.9 -> 34.9Hurt
replace GRAM volume loss with singular-value softmax lossPMRL vs GRAM · ABIDE autism classificationAUC: 63.9 -> 80.5Improved
replace GRAM with PMRL on fine-tuned MSR-VTT retrieval (vs VAST)PMRL · MSR-VTT text-to-video (fine-tuned)Recall@1: 64.4 -> 61.2Hurt
add PMRL objective to VAST on VATEX fine-tuned retrievalVAST · VATEX text-to-video (fine-tuned)Recall@1: 83.1 -> 84.1Improved
add PMRL objective to VAST on Houston13VAST · Houston13 hyperspectral classificationoverall accuracy: 7.17 -> 26.51Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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