Research map / Vision-language and multimodal / Visual question answering
VistaNet: Visual Aspect Attention Network for Multimodal Sentiment Analysis
Quoc-Tuan Truong, Hady W. Lauw
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use images as attention over sentences instead of as features | multimodal sentiment model · Yelp avg | accuracy: 55.01 -> 61.88 | Improved |
| tensor fusion of text and image features | HAN text features · Yelp avg | accuracy: 55.01 -> 46.87 | Hurt |
| max-pooling instead of average pooling of image features | BiGRU-VGG · Yelp avg | accuracy: 49.32 -> 52.20 | Improved |
| add hierarchical document structure (ablation) | BiRNN text model · Yelp avg | accuracy: 56.83 -> 59.54 | Improved |
| add soft text attention (ablation) | hierarchical BiRNN · Yelp avg | accuracy: 59.54 -> 60.56 | Improved |
| add visual aspect attention (ablation) | hierarchical BiRNN with text attention · Yelp avg | accuracy: 60.56 -> 61.88 | Improved |
| increase number of images from MEAN only to MEAN+3 (ablation) | VistaNet · Yelp avg | accuracy: 60.61 -> 61.88 | Improved |
Closest papers by meaning
- TextGT: A Double-View Graph Transformer on Text for Aspect-Based Sentiment Analysis (AAAI 2024 · similarity 0.85)
- DEQA: Descriptions Enhanced Question-Answering Framework for Multimodal Aspect-Based Sentiment Analysis (AAAI 2025 · similarity 0.85)
- You Only Read Once: Constituency-Oriented Relational Graph Convolutional Network for Multi-Aspect Multi-Sentiment Classification (AAAI 2024 · similarity 0.85)
- A Novel Energy Based Model Mechanism for Multi-Modal Aspect-Based Sentiment Analysis (AAAI 2024 · similarity 0.84)
- Seek Common Ground While Reserving Differences: Semi-Supervised Image-Text Sentiment Recognition (CVPR 2025 · similarity 0.84)
- Aspect Enhancement and Text Simplification in Multimodal Aspect-Based Sentiment Analysis for Multi-Aspect and Multi-Sentiment Scenarios (AAAI 2025 · similarity 0.83)
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.
