AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Weakly Supervised Coupled Networks for Visual Sentiment Analysis

Jufeng Yang, Dongyu She, Yu-Kun Lai, Paul L. Rosin, Ming-Hsuan Yang

CVPR 2018 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 166 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 WSCNet instead of WILDCATResNet-101 · FI testaccuracy: 70.07 vs 67.03Improved
Use WSCNet instead of WILDCATResNet-101 · Flickr testaccuracy: 81.36 vs 80.67Improved
Use WSCNet instead of WILDCATResNet-101 · Instagram testaccuracy: 81.81 vs 80.31Improved
Use WSCNet instead of WILDCATResNet-101 · EmotionROI testaccuracy: 58.25 vs 55.05Improved
Use WSCNet instead of SPNResNet-101 · Twitter I testaccuracy: 84.25 vs 81.67Improved
Use WSCNet instead of Sun et al.ResNet-101 · Twitter II testaccuracy: 81.35 vs 80.84Improved
Use 4 feature maps per sentiment class rather than 1 (ablation)WSCNet · FI testaccuracy: 68.23 -> 70.07Improved
Use more than 4 feature maps per sentiment class (ablation)WSCNet · FI testaccuracy: 70.07 -> 68.80; 70.07 -> 67.19Hurt
Vary the number of feature maps from 1 to 16 (ablation)WSCNet · Flickr testaccuracy: 81.46; 81.87; 81.36; 81.15; 81.98Mixed
Vary the number of feature maps from 1 to 16 (ablation)WSCNet · Instagram testaccuracy: 79.67; 79.24; 81.80; 79.60; 78.53Mixed
Add multiple feature maps (k=4) and sentiment-map coupling instead of the baseline without coupling (ablation)WSCNet · FI testaccuracy: 66.57 -> 70.07Improved
Add sentiment-map guidance to the k=4 model (ablation)WSCNet · FI testaccuracy: 67.96 -> 67.69Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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