You are here

Simple vs complex temporal recurrences for video saliency prediction


Panagiotis Linardos, Eva Mohedano, Juan Jose Nieto, Noel O'Connor, Xavier Giro-i-Nieto, Kevin McGuinness

Publication Type: 
Refereed Conference Meeting Proceeding
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 computationally 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.
Conference Name: 
British Machine Vision Conference (BMVC) 2019
Proceedings of the British Machine Vision Conference (BMVC) 2019
Digital Object Identifer (DOI): 
Publication Date: 
Conference Location: 
United Kingdom (excluding Northern Ireland)
Research Group: 
Dublin City University (DCU)
Open access repository: