DeepSentiBank: Visual Sentiment Concept Classification with Deep Convolutional Neural Networks
By Tao Chen, Damian Borth, Trevor Darrell, Shih-Fu Chang. arXiv.org, 2014
314 citations recorded by the source corpus.
This paper introduces a visual sentiment concept classification method based on deep convolutional neural networks (CNNs). The visual sentiment concepts are adjective noun pairs (ANPs) automatically discovered from the tags of web photos, and can be utilized as effective statistical cues for detecting emotions depicted in the images. Nearly one million Flickr images tagged with these ANPs are downloaded to train the classifiers of the concepts. We adopt the popular model of deep convolutional neural networks which recently shows great performance improvement on classifying large-scale web-based image dataset such as ImageNet. Our deep CNNs model is trained based on Caffe, a newly developed deep learning framework. To deal with the biased training data which only contains images with strong sentiment and to prevent overfitting, we initialize the model with the model weights trained from ImageNet. Performance evaluation shows the newly trained deep CNNs model SentiBank 2.0 (or called DeepSentiBank) is significantly improved in both annotation accuracy and retrieval performance, compared to its predecessors which mainly use binary SVM classification models.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/d9244ec86920e81f91f9599628b06693dec76028
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Maja Pantic
- Marcel Worring
- Mohammad Soleymani
- Björn Schuller
- Brendan Jou
- David García
- Shih-Fu Chang
- Florian Eyben
In Computer Vision and Pattern Recognition
- Maja Pantic
- Björn Schuller
- Marcel Worring
- Shih-Fu Chang
- Mohammad Soleymani
- Brendan Jou
- David García
- Luc Van Gool
Citations in the corpus
- A survey of multimodal sentiment analysis (2017, methodology): “[127] proposed an AlexNet model fined-tuned from an ImageNet model for an expanded set of 2089 ANPs in VSO [14] with a top-5 accuracy of 19.”
- What you Feel, Is what you like Influence of Message Appeals on Customer Engagement on Instagram (2020, background): “A number of approaches attempt to model visual valence and arousal (Borth et al. 2013; Chen et al. 2014).”