Hierarchical Representations for Spatio-Temporal Visual Attention Modeling and Understanding
Computer Vision and Pattern Recognition
2023-08-11 v1 Artificial Intelligence
Machine Learning
Abstract
This PhD. Thesis concerns the study and development of hierarchical representations for spatio-temporal visual attention modeling and understanding in video sequences. More specifically, we propose two computational models for visual attention. First, we present a generative probabilistic model for context-aware visual attention modeling and understanding. Secondly, we develop a deep network architecture for visual attention modeling, which first estimates top-down spatio-temporal visual attention, and ultimately serves for modeling attention in the temporal domain.
Cite
@article{arxiv.2308.05189,
title = {Hierarchical Representations for Spatio-Temporal Visual Attention Modeling and Understanding},
author = {Miguel-Ángel Fernández-Torres},
journal= {arXiv preprint arXiv:2308.05189},
year = {2023}
}
Comments
PhD thesis