What do different evaluation metrics tell us about saliency models?

Z Bylinskii, T Judd, A Oliva, A Torralba… - IEEE transactions on …, 2018 - ieeexplore.ieee.org
How best to evaluate a saliency model's ability to predict where humans look in images is an
open research question. The choice of evaluation metric depends on how saliency is …

Review of visual saliency prediction: Development process from neurobiological basis to deep models

F Yan, C Chen, P Xiao, S Qi, Z Wang, R Xiao - Applied Sciences, 2021 - mdpi.com
The human attention mechanism can be understood and simulated by closely associating
the saliency prediction task to neuroscience and psychology. Furthermore, saliency …

Uniform competency-based local feature extraction for remote sensing images

A Sedaghat, N Mohammadi - ISPRS Journal of Photogrammetry and …, 2018 - Elsevier
Local feature detectors are widely used in many photogrammetry and remote sensing
applications. The quantity and distribution of the local features play a critical role in the …

Using information content to select keypoints for UAV image matching

V Mousavi, M Varshosaz, F Remondino - Remote Sensing, 2021 - mdpi.com
Image matching is one of the most important tasks in Unmanned Arial Vehicles (UAV)
photogrammetry applications. The number and distribution of extracted keypoints play an …

Sid4vam: A benchmark dataset with synthetic images for visual attention modeling

D Berga, XR Fdez-Vidal, X Otazu… - Proceedings of the …, 2019 - openaccess.thecvf.com
A benchmark of saliency models performance with a synthetic image dataset is provided.
Model performance is evaluated through saliency metrics as well as the influence of model …

A biologically inspired framework for visual information processing and an application on modeling bottom-up visual attention

A Aboudib, V Gripon, G Coppin - Cognitive computation, 2016 - Springer
Background An emerging trend in visual information processing is toward incorporating
some interesting properties of the ventral stream in order to account for some limitations of …

Improving SURF image matching using supervised learning

HM Sergieh, E Egyed-Zsigmond… - … on Signal Image …, 2012 - ieeexplore.ieee.org
Key points-based image matching algorithms have proven very successful in recent years.
However, their execution time makes them unsuitable for online applications. Indeed …

Geospatial target detection from high-resolution remote-sensing images based on PIIFD descriptor and salient regions

F Ghorbani, H Ebadi, A Sedaghat - Journal of the Indian Society of Remote …, 2019 - Springer
Geospatial target detection from visible remote-sensing images is considered as one of the
most important issues in the analysis of aerial and satellite imagery. Development of remote …

Visual language modeling on cnn image representations

H Kato, T Harada - arXiv preprint arXiv:1511.02872, 2015 - arxiv.org
Measuring the naturalness of images is important to generate realistic images or to detect
unnatural regions in images. Additionally, a method to measure naturalness can be …

The effect of eye movements in response to different types of scenes using a graph-based visual saliency algorithm

M Wahid, A Waris, SO Gilani, R Subramanian - Applied Sciences, 2019 - mdpi.com
Saliency is the quality of an object that makes it stands out from neighbouring items and
grabs viewer attention. Regarding image processing, it refers to the pixel or group of pixels …