Temporal recurrences for video saliency prediction
Year: 2019
Type: conference-paper
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.
Authors: Panagiotis Linardos, Eva Mohedano, Juanjo Nieto, Noel E. O’Connor, Xavier Giró-i-Nieto, Kevin McGuinness
Institutions: Dublin City University, Universitat Politècnica de Catalunya
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3125252836
