AI Paper Atlas

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

An Efficient Approach to Informative Feature Extraction from Multimodal Data

AAAI 2019 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal sentiment analysis · 64 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 supervised label loss to Soft-HGRSoft-HGR on XRMB · XRMB phonetic prediction, 10% labelsaccuracy: 72.2% -> 76.3%Helped
Add supervised label loss to Soft-HGRSoft-HGR on XRMB · XRMB phonetic prediction, 50% labelsaccuracy: 81.2% -> 85.0%Helped
Add supervised label loss to Soft-HGRSoft-HGR on XRMB · XRMB phonetic prediction, 100% labelsaccuracy: 86.4% -> 88.0%Helped
Add the Soft-HGR objective to the predictive model (ablation)Semi Soft-HGR on KKBox · KKBox, no missing labels or modalitiesAUCHelped
Use unsupervised Soft-HGR alongside supervised trainingSemi Soft-HGR on KKBox · KKBox, no missing labels or modalitiesAUC: 0.6803 -> 0.6972Helped
Use multimodal semi-supervised Soft-HGR with incomplete modalitiesSemi Soft-HGR on KKBox · KKBox, 50% missing modalitiesAUC: 0.6574 -> 0.6682Helped

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