Selection of a best metric and evaluation of bottom-up visual saliency models

2013 ◽  
Vol 31 (10) ◽  
pp. 796-808 ◽  
Author(s):  
Mohsen Emami ◽  
Lawrence L. Hoberock
Keyword(s):  
Visual Saliency ◽  
Bottom Up ◽  
Visual Saliency Models ◽  
Selection Of

scholarly journals Recent Advances in Saliency Estimation for Omnidirectional Images, Image Groups, and Video Sequences

2020 ◽  
Vol 10 (15) ◽  
pp. 5143
Author(s):  
Marco Buzzelli
Keyword(s):  
Evaluation Criteria ◽  
Visual Saliency ◽  
Ground Truth ◽  
Video Sequences ◽  
Domain Specific ◽  
Saliency Maps ◽  
Perceptual Property ◽  
Omnidirectional Images ◽  
Video Saliency ◽  
Selection Of

We present a review of methods for automatic estimation of visual saliency: the perceptual property that makes specific elements in a scene stand out and grab the attention of the viewer. We focus on domains that are especially recent and relevant, as they make saliency estimation particularly useful and/or effective: omnidirectional images, image groups for co-saliency, and video sequences. For each domain, we perform a selection of recent methods, we highlight their commonalities and differences, and describe their unique approaches. We also report and analyze the datasets involved in the development of such methods, in order to reveal additional peculiarities of each domain, such as the representation used for the ground truth saliency information (scanpaths, saliency maps, or salient object regions). We define domain-specific evaluation measures, and provide quantitative comparisons on the basis of common datasets and evaluation criteria, highlighting the different impact of existing approaches on each domain. We conclude by synthesizing the emerging directions for research in the specialized literature, which include novel representations for omnidirectional images, inter- and intra- image saliency decomposition for co-saliency, and saliency shift for video saliency estimation.

scholarly journals Understanding and Visualizing Deep Visual Saliency Models

2019 ◽  
Author(s):  
Sen He ◽  
Hamed R. Tavakoli ◽  
Ali Borji ◽  
Yang Mi ◽  
Nicolas Pugeault
Keyword(s):  
Visual Saliency ◽  
Visual Saliency Models

scholarly journals Top-down or bottom-up? The selection of shadow rapporteurs in the European Parliament

2020 ◽  
Vol 21 (4) ◽  
pp. 706-727
Author(s):  
Frank M Häge ◽  
Nils Ringe
Keyword(s):  
European Parliament ◽  
Third Party ◽  
Top Down ◽  
Bottom Up ◽  
Principal Agent Theory ◽  
Policy Positions ◽  
Competing Demands ◽  
Group Members ◽  
Selection Of

Shadow rapporteurs play an important role in developing the European Parliament’s collective policy positions and in defending them in inter-institutional negotiations. This study sheds light on the ‘how’ and ‘why’ of shadow rapporteur selection. Qualitative insights from practitioner interviews and a quantitative analysis of shadow rapporteur data from the 7th European Parliament (2009–2014) indicate that the appointment process is primarily one of bottom-up self-selection by group members based on their policy interests. The party group leadership, in the form of group coordinators, plays an important coordinating role when there is competition for a shadow rapporteurship. However, the role of group coordinators is more akin to a third-party arbiter of competing demands than a mechanism of top-down control by the leadership, as suggested by principal-agent theory.

scholarly journals Prioritizing selection of new elements: Bottom-up versus top-down control

2003 ◽  
Vol 65 (8) ◽  
pp. 1231-1242 ◽  
Author(s):  
Mieke Donk ◽  
Jan Theeuwes
Keyword(s):  
Top Down ◽  
Bottom Up ◽  
Selection Of

ARTISTIC COMPLEXITY AND SALIENCY: TWO FACES OF THE SAME COIN?

2013 ◽  
Vol 09 (02) ◽  
pp. 1350010 ◽  
Author(s):  
MATTEO CACCIOLA ◽  
GIANLUIGI OCCHIUTO ◽  
FRANCESCO CARLO MORABITO
Keyword(s):  
Information Content ◽  
Visual Saliency ◽  
Relevant Information ◽  
Human Observer ◽  
Top Down ◽  
Complexity Measures ◽  
Bottom Up ◽  
Content Description ◽  
Brain Processing ◽  
The Brain

Many computer vision problems consist of making a suitable content description of images usually aiming to extract the relevant information content. In case of images representing paintings or artworks, the information extracted is rather subject-dependent, thus escaping any universal quantification. However, we proposed a measure of complexity of such kinds of oeuvres which is related to brain processing. The artistic complexity measures the brain inability to categorize complex nonsense forms represented in modern art, in a dynamic process of acquisition that most involves top-down mechanisms. Here, we compare the quantitative results of our analysis on a wide set of paintings of various artists to the cues extracted from a standard bottom-up approach based on visual saliency concept. In every painting inspection, the brain searches for more informative areas at different scales, then connecting them in an attempt to capture the full impact of information content. Artistic complexity is able to quantify information which might have been individually lost in the fruition of a human observer thus identifying the artistic hand. Visual saliency highlights the most salient areas of the paintings standing out from their neighbours and grabbing our attention. Nevertheless, we will show that a comparison on the ways the two algorithms act, may manifest some interesting links, finally indicating an interplay between bottom-up and top-down modalities.

Bottom–Up Visual Saliency Estimation With Deep Autoencoder-Based Sparse Reconstruction

2016 ◽  
Vol 27 (6) ◽  
pp. 1227-1240 ◽  
Author(s):  
Chen Xia ◽  
Fei Qi ◽  
Guangming Shi
Keyword(s):  
Visual Saliency ◽  
Sparse Reconstruction ◽  
Bottom Up

Ray Saliency: Bottom-Up Visual Saliency for a Rotating and Zooming Camera

2015 ◽  
Vol 116 (2) ◽  
pp. 174-189
Author(s):  
Garrett Warnell ◽  
Philip David ◽  
Rama Chellappa
Keyword(s):  
Visual Saliency ◽  
Bottom Up
Sign in / Sign up

Export Citation Format

Share Document