AI Paper Atlas

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

Learning Multimodal Word Representation via Dynamic Fusion Methods

Shaonan Wang, Jiajun Zhang, Chengqing Zong

AAAI 2018 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 36 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
Use dynamic fusion with vector gates instead of RidgeMultimodal word representations · VIS and ZS regions across six benchmarksSpearman correlationImproved
Use vector gates rather than value gates (ablation)M-gate, C-gate, and S-gate · Six evaluation benchmarksSpearman correlationImproved
Use category-specific vector gating instead of modality- or sample-specific vector gating (ablation)Dynamic fusion · Six evaluation benchmarksSpearman correlationHurt
Reduce training data for vector-gate models (ablation)Dynamic fusion with vector gates · All evaluation benchmarksaverage Spearman correlationHurt
Reduce training data for value-gate models (ablation)Dynamic fusion with value gates · All evaluation benchmarksaverage Spearman correlationNo clear effect
Concatenate original visual vectors with linguistic vectors instead of using predicted visual vectorsCONC · Four of six benchmarksSpearman correlationHurt
Use predicted visual vectors with Mapping or Ridge instead of linguistic vectors aloneMapping and Ridge · Five of six benchmarks, ALL and VISSpearman correlationImproved
Use Mapping or Ridge instead of Glove aloneMapping and Ridge · ZS regionSpearman correlationMixed
Use vector gates rather than value gates (ablation)Dynamic fusion models · All six evaluation benchmarksSpearman correlationImproved
Use S-gate-val (ablation)Sample-specific fusion · USF concreteness wordsSpearman correlation (concreteness vs. linguistic-to-visual weight ratio): 0.614Improved
Use S-gate-vec (ablation)Sample-specific fusion · USF concreteness wordsSpearman correlation (concreteness vs. linguistic-to-visual weight ratio): 0.458Improved

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