Idioma:

From pixels to sentiment: Fine-tuning CNNs for visual sentiment prediction

Campos, Víctor ; Jou, Brendan ; Giró-i-Nieto, Xavier

Image and vision computing, 2017-09, Vol.65, p.15-22 [Periódico revisado por pares]

Elsevier B.V

Texto completo disponível

Citações Citado por

Enviar para

Título:
From pixels to sentiment: Fine-tuning CNNs for visual sentiment prediction
Autor: Campos, Víctor ; Jou, Brendan ; Giró-i-Nieto, Xavier
Assuntos: Convolutional Neural Networks ; Digital techniques ; Enginyeria de la telecomunicació ; Fine-tuning strategies ; Image processing ; Imatges ; Multimedia systems ; Neural networks (Computer science) ; Processament ; Processament de la imatge i del senyal vídeo ; Processament del senyal ; Sentiment ; Sistemes multimèdia ; Social media ; Social multimedia ; Social networks ; Tècniques digitals ; Xarxes neuronals (Informàtica) ; Xarxes socials ; Àrees temàtiques de la UPC
É parte de: Image and vision computing, 2017-09, Vol.65, p.15-22
Descrição: Visual multimedia have become an inseparable part of our digital social lives, and they often capture moments tied with deep affections. Automated visual sentiment analysis tools can provide a means of extracting the rich feelings and latent dispositions embedded in these media. In this work, we explore how Convolutional Neural Networks (CNNs), a now de facto computational machine learning tool particularly in the area of Computer Vision, can be specifically applied to the task of visual sentiment prediction. We accomplish this through fine-tuning experiments using a state-of-the-art CNN and via rigorous architecture analysis, we present several modifications that lead to accuracy improvements over prior art on a dataset of images from a popular social media platform. We additionally present visualizations of local patterns that the network learned to associate with image sentiment for insight into how visual positivity (or negativity) is perceived by the model. [Display omitted] •A visual sentiment prediction framework using a Convolutional Neural Network•Comparison of several performance boosting strategies•6.1% absolute accuracy improvement over the previous state-of-the-art•Visualization of local patterns associated to each image's sentiment
Editor: Elsevier B.V
Idioma: Inglês

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

From pixels to sentiment: Fine-tuning CNNs for visual sentiment prediction

Campos, Víctor ; Jou, Brendan ; Giró-i-Nieto, Xavier

Elsevier B.V

Buscando em bases de dados remotas. Favor aguardar.