AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Multi-Interactive Memory Network for Aspect Based Multimodal Sentiment Analysis

AAAI 2019 · Vision-language and multimodal › Human and embodied modeling · approach: Multimodal retrieval-augmented modeling · 254 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 image modality with multi-interactive memory network vs best multimodal baselineaspect-level sentiment model · Multi-ZOLaccuracy: 60.43 -> 61.59Helped
add cross-modality attention (vs self-only) (ablation)MIMN · Multi-ZOLaccuracy: 60.50 -> 61.59Helped
add image2text attention (ablation)MIMN · Multi-ZOLaccuracy: 61.17 -> 61.59Helped
add text2image attention (ablation)MIMN · Multi-ZOLaccuracy: 61.23 -> 61.59Helped
increase memory hops from 1 to 3 (ablation)MIMN · Multi-ZOLaccuracy: 60.08 -> 61.59Helped
increase memory hops beyond 3 (to 5) (ablation)MIMN · Multi-ZOLaccuracy: 61.59 -> 60.11Hurt

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