Abstract This paper investigates modifying an existing neural network architecture for static saliency prediction using two types of recurrences that integrate information from the temporal domain. The first modification is the addition of a ConvLSTM within the architecture, while the second is a conceptually simple exponential moving average of an internal convolutional state. We use weights pre-trained on the SALICON dataset and fine-tune our model on DHF1K. Our results show that both modifications achieve state-of-the-art results and produce similar saliency maps. Source code is available at https://git.io/fjPiB.

Url http://doras.dcu.ie/23568/2/SUBMISSION.pdf

Collections Ireland -> Dublin City University -> Publication Type = Conference or Workshop Item
Ireland -> Dublin City University -> Subject = Computer Science: Artificial intelligence
Ireland -> Dublin City University -> Subject = Computer Science: Image processing
Ireland -> Dublin City University -> Status = Submitted
Ireland -> Dublin City University -> DCU Faculties and Centres = DCU Faculties and Schools: Faculty of Engineering and Computing: School of Electronic Engineering
Ireland -> Dublin City University -> Subject = Computer Science: Digital video
Ireland -> Dublin City University -> DCU Faculties and Centres = Research Initiatives and Centres: INSIGHT Centre for Data Analytics
Ireland -> Dublin City University -> Subject = Computer Science: Machine learning