Predicting Image Emotion Distribution by Emotional Region

Recent studies on image emotion prediction mainly focus on classifying images into a certain emotion category, but single label cannot reflect peoples' multiple emotion to image. To get more realistic results, we study image emotion distribution problem. In the most image emotion tasks, features are extracted from the whole image, but not each part makes contribution to emotion, so features from the whole image contain noises. In order to get discriminative features, we propose to leverage the heatmap generated by Fully Convolutional Networks (FCN) to select the Region of Interest (ROI) from an image which represents the image emotion most. Both high-level features and hand-crafted features from ROI are fused to train Support Vector Regressors (SVRs) to predict emotion distribution. Extensive experiments conducted on two widely used datasets demonstrate that emotional region is selected out through our method so that emotion distribution prediction performances are improved.

• Publication year

  2018

• Venue

  2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

• Publication date

  2018-10-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/CISP-BMEI.2018.8633190
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Discrete Probability Distribution Prediction of Image Emotions with Shared Sparse Learning

  2020cited by this paper
• Learning Visual Sentiment Distributions via Augmented Conditional Probability Neural Network

  2017cited by this paper
• High-Level Concepts for Affective Understanding of Images

  2017cited by this paper
• Approximating Discrete Probability Distribution of Image Emotions by Multi-Modal Features Fusion

  2017cited by this paper
• Where do emotions come from? Predicting the Emotion Stimuli Map

  2016influential reference
• From pixels to sentiment: Fine-tuning CNNs for visual sentiment prediction

  2016cited by this paper
• Multi-scale blocks based image emotion classification using multiple instance learning

  2016cited by this paper
• Discovering affective regions in deep convolutional neural networks for visual sentiment prediction

  2016influential reference
• Learning Multi-level Deep Representations for Image Emotion Classification

  2016cited by this paper
• A mixed bag of emotions: Model, predict, and transfer emotion distributions

  2015cited by this paper
• Predicting discrete probability distribution of image emotions

  2015cited by this paper
• Exploring Principles-of-Art Features For Image Emotion Recognition

  2014influential reference
• Fully convolutional networks for semantic segmentation

  2014influential reference
• Object-Based Visual Sentiment Concept Analysis and Application

  2014cited by this paper
• Interpretable aesthetic features for affective image classification

  2013cited by this paper
• Large-scale visual sentiment ontology and detectors using adjective noun pairs

  2013cited by this paper
• Context-aware affective images classification based on bilayer sparse representation

  2012cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• A multi-layer hybrid framework for dimensional emotion classification

  2011cited by this paper
• Analyzing and predicting sentiment of images on the social web

  2010cited by this paper
• Facial Age Estimation by Learning from Label Distributions

  2010cited by this paper
• Affective image classification using features inspired by psychology and art theory

  2010cited by this paper
• Emotional category data on images from the international affective picture system

  2005cited by this paper
• An argument for basic emotions

  1992cited by this paper
• Three dimensions of emotion.

  1954cited by this paper

• Emotion-wise feature interaction analysis-based visual emotion distribution learning

  2023cites this paper
• Context-Aware Multi-Stream Networks for Dimensional Emotion Prediction in Images

  2023cites this paper
• StyleEDL: Style-Guided High-order Attention Network for Image Emotion Distribution Learning

  2023cites this paper
• Machine Learning-Based Emotional Recognition in Surveillance Video Images in the Context of Smart City Safety

  2021cites this paper
• Visual Sentiment Analysis for Few-Shot Image Classification Based on Metric Learning

  2020cites this paper
• Emotional Understanding of an Image by Applying High-level Concepts on Image Parts

  2020cites this paper
• Outlier Processing in Multimodal Emotion Recognition

  2020cites this paper
• Median based Multi-label Prediction by Inflating Emotions with Dyads for Visual Sentiment Analysis

  2019cites this paper