Simple vs complex temporal recurrences for video saliency prediction
| Autor: | Linardos, P., Mohedano, E., Nieto, J. J., O Connor, N. E., Giro-I-Nieto, X., Kevin McGuinness |
|---|---|
| Přispěvatelé: | Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions, Universitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Artificial intelligence Computer Science - Machine Learning Saliency Computer Vision and Pattern Recognition (cs.CV) Digital video Visió per ordinador Computer Science - Computer Vision and Pattern Recognition Deep learning Video Machine Learning (cs.LG) Neural networks (Computer science) Image processing Machine learning Xarxes neuronals (Informàtica) Informàtica::Intel·ligència artificial [Àrees temàtiques de la UPC] Computer vision Aprenentatge profund |
| Zdroj: | Linardos, Panagiotis, Mohedano, Eva, Nieto, Juan Jose, O'Connor, Noel E. ORCID: 0000-0002-4033-9135 UPCommons. Portal del coneixement obert de la UPC Universitat Politècnica de Catalunya (UPC) Scopus-Elsevier |
| Popis: | 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. Accepted at BMVC 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|