AI Paper Atlas

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

Preserving Modality Structure Improves Multi-Modal Learning

Sirnam Swetha, Mamshad Nayeem Rizve, Nina Shvetsova, Hilde Kuehne, Mubarak Shah

ICCV 2023 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 4 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
replace SSPC loss with reconstruction loss plus contrastive loss (ablation)Semantic-structure-preserving consistency method · MSR-VTT zero-shot retrievalR@5: 25.1 -> 23.1Hurt
add cross-modal SSPC loss (ablation)Semantic-structure-preserving consistency method · MSR-VTT zero-shot retrievalR@5: 22.7 -> 25.1Improved
add cross-modal SSPC loss (ablation)Semantic-structure-preserving consistency method · YouCook2 zero-shot retrievalR@5: 36.9 -> 39.4Improved
add anchor consistency between modality-specific and joint embedding spaces (SSPC loss) (ablation)Semantic-structure-preserving consistency method · MSR-VTT zero-shot retrievalR@5: 23.8 -> 25.1Improved
use proposed Multi-SK algorithm instead of modified vanilla Sinkhorn-Knopp (ablation)Semantic-structure-preserving consistency method · MSR-VTT zero-shot retrievalR@5: 23.4 -> 25.1Improved
increase number of anchors K from 16 to 64 (with K' fixed proportionally) (ablation)Semantic-structure-preserving consistency method · MSR-VTT zero-shot retrievalR@5: 23.1 -> 25.1Improved
select 48 of 64 anchors instead of 32 (ablation)Semantic-structure-preserving consistency method · MSR-VTT zero-shot retrievalR@5: 25.1 -> 23.7Hurt
use learned multi-anchor structure preservation versus EAO baseline on out-of-domain MSR-VTT (fine-tune)Semantic-structure-preserving consistency method · MSR-VTT t->v fine-tuneR@5: 47.7 -> 48.7Improved
proposed method versus EAO on zero-shot text-to-full-video retrievalSemantic-structure-preserving consistency method · YouCook2 zero-shot full videoR@1: 62.9 -> 65.1Improved

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