Visual media are powerful means of expressing emotions and sentiments. The constant generation of new content in social networks highlights the need of automated visual sentiment analysis tools. While Convolutional Neural Networks (CNNs) have established a new state-of-the-art in several vision problems, their application to the task of sentiment analysis is mostly unexplored and there are few studies regarding how to design CNNs for this purpose. In this work, we study the suitability of fine-tuning a CNN for visual sentiment prediction as well as explore performance boosting techniques within this deep learning setting. Finally, we provide a deep-dive analysis into a benchmark, state-of-the-art network architecture to gain insight about how to design patterns for CNNs on the task of visual sentiment prediction.
@article{arxiv.1508.05056,
title = {Diving Deep into Sentiment: Understanding Fine-tuned CNNs for Visual Sentiment Prediction},
author = {Victor Campos and Amaia Salvador and Brendan Jou and Xavier Giró-i-Nieto},
journal= {arXiv preprint arXiv:1508.05056},
year = {2015}
}
Comments
Preprint of the paper accepted at the 1st Workshop on Affect and Sentiment in Multimedia (ASM), in ACM MultiMedia 2015. Brisbane, Australia