AI Paper Atlas

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

What Makes Multi-Modal Learning Better than Single (Provably)

Yu Huang, Chenzhuang Du, Zihui Xue, Xuanyao Chen, Hang Zhao, Longbo Huang

NeurIPS 2021 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 43 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 Video to TextIEMOCAP late-fusion classifier · IEMOCAP testtop-1 accuracy: 49.93$\pm$0.57 -> 51.08$\pm$0.66Improved
Add Audio to TextIEMOCAP late-fusion classifier · IEMOCAP testtop-1 accuracy: 49.93$\pm$0.57 -> 53.03$\pm$0.21Improved
Add Audio to Text + VideoIEMOCAP late-fusion classifier · IEMOCAP testtop-1 accuracy: 51.08$\pm$0.66 -> 53.89 $\pm$ 0.47Improved
Add modalities beyond m1Synthetic-data MLP · Synthetic data, overlap 0.0MSE loss: 301.92$\pm$7.85 -> 207.45$\pm$4.68 -> 103.23$\pm$0.61 -> 0Improved
Add modalities beyond m1Synthetic-data MLP · Synthetic data, overlap 0.2MSE loss: 193.28$\pm$1.08 -> 129.81$\pm$4.36 -> 65.17$\pm$1.52 -> 0Improved
Add modalities beyond m1Synthetic-data MLP · Synthetic data, overlap 0.5MSE loss: 75.89$\pm$1.28 -> 51.25$\pm$1.06 -> 26.06$\pm$0.69 -> 0Improved
Add modalities beyond m1Synthetic-data MLP · Synthetic data, overlap 0.8MSE loss: 12.04$\pm$0.39 -> 8.16$\pm$0.17 -> 4.18$\pm$0.05 -> 0Improved
Add modalities beyond m1Synthetic-data MLP · Synthetic data, overlap 1MSE loss: 0 -> 0 -> 0 -> 0No clear effect
Use all three modalities rather than Text aloneIEMOCAP late-fusion classifier · IEMOCAP test, sample ratio $10^{-3}$top-1 accuracy: 29.08$\pm$3.34 -> 32.24$\pm$1.17Mixed
Use all three modalities rather than Text aloneIEMOCAP late-fusion classifier · IEMOCAP test, sample ratio $10^{-2}$top-1 accuracy: 45.63$\pm$0.29 -> 46.39$\pm$3.82Mixed
Increase the training sample ratioIEMOCAP modality settings · IEMOCAP testtop-1 accuracy: T: 23.66$\pm$1.28 -> 49.93$\pm$0.57; TA: 25.06$\pm$1.05 -> 51.08$\pm$0.66; TV: 24.71$\pm$0.87 -> 53.03$\pm$0.21; TVA: 24Improved

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