AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Deep Multimodal Multilinear Fusion with High-order Polynomial Pooling

Ming Hou, Jiajia Tang, Jianhai Zhang, Wanzeng Kong, Qibin Zhao

NeurIPS 2019 · Architectures and efficiency › CNN design · approach: Higher-order pooling · 66 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 hierarchical second PTP layer to single-layer HPFN (ablation)HPFN · CMU-MOSIAcc-7: 35.9 -> 36.3Improved
stack to four layers instead of two (ablation)HPFN-L2 · CMU-MOSIAcc-7: 36.3 -> 34.6Hurt
add dense skip connections of unimodal features to two-layer HPFN (ablation)HPFN-L2 · CMU-MOSIAcc-7: 36.3 -> 36.5Improved
add a third layer to two-layer HPFN (ablation)HPFN-L2 · CMU-MOSIAcc-7: 36.3 -> 36.0Hurt
use temporal overlapped windows instead of time-averaged non-temporal features (ablation)HPFN-L2 · CMU-MOSIMAE: 0.958 -> 0.944Improved
share a single PTP across temporal windows (ablation)temporal HPFN-L2 · CMU-MOSIAcc-7: 36.7 -> 35.7Hurt
fuse all three modalities instead of text only (ablation)HPFN P=[4] · CMU-MOSIAcc-7: 35.1 -> 36.0Improved
vary polynomial order from 1 to 10 (ablation)HPFN · CMU-MOSIAcc-2/F1Mixed
use HPFN-L2 instead of LMFIEMOCAP · IEMOCAPF1-Angry: 89.0 -> 88.8Hurt
use HPFN-L2 instead of LMFCMU-MOSI · CMU-MOSIMAE: 0.912 -> 0.945Hurt

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