AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

VistaNet: Visual Aspect Attention Network for Multimodal Sentiment Analysis

Quoc-Tuan Truong, Hady W. Lauw

AAAI 2019 · Vision-language and multimodal › Visual question answering · approach: Multimodal LLM question answering · 155 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 images as attention over sentences instead of as featuresmultimodal sentiment model · Yelp avgaccuracy: 55.01 -> 61.88Improved
tensor fusion of text and image featuresHAN text features · Yelp avgaccuracy: 55.01 -> 46.87Hurt
max-pooling instead of average pooling of image featuresBiGRU-VGG · Yelp avgaccuracy: 49.32 -> 52.20Improved
add hierarchical document structure (ablation)BiRNN text model · Yelp avgaccuracy: 56.83 -> 59.54Improved
add soft text attention (ablation)hierarchical BiRNN · Yelp avgaccuracy: 59.54 -> 60.56Improved
add visual aspect attention (ablation)hierarchical BiRNN with text attention · Yelp avgaccuracy: 60.56 -> 61.88Improved
increase number of images from MEAN only to MEAN+3 (ablation)VistaNet · Yelp avgaccuracy: 60.61 -> 61.88Improved

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