Existing saliency detection approaches use images as inputs and are sensitive to foreground/background similarities, complex background textures, and occlusions. We explore the problem of using light fields as input for saliency detection. Our technique is enabled by the availability of commercial plenoptic cameras that capture the light field of a scene in a single shot. We show that the unique refocusing capability of light fields provides useful focusness, depths, and objectness cues. We further develop a new saliency detection algorithm tailored for light fields. To validate our approach, we acquire a light field database of a range of indoor and outdoor scenes and generate the ground truth saliency map. Experiments show that our saliency detection scheme can robustly handle challenging scenarios such as similar foreground and background, cluttered background, complex occlusions, etc., and achieve high accuracy and robustness.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TPAMI.2016.2610425 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
The Impact of Motivation on Sustained Attention in Very Preterm and Term-born Children: An ERP Study.
J Atten Disord
January 2025
School of Psychology, University of Nottingham, UK.
Objective: To compare the effect of motivational features on sustained attention in children born very preterm and at term.
Method: EEG was recorded while 34 8-to-11-year-old children born very preterm and 34 term-born peers completed two variants of a cued continuous performance task (CPT-AX); a standard CPT-AX with basic shape stimuli, and structurally similar variant, with a storyline, familiar characters, and feedback.
Results: Higher hit rates, quicker response times and larger event-related potential (ERP) amplitudes were observed during the motivating, compared with the standard, task.
Background: Tau protein accumulation is closely linked to synaptic and neuronal loss in Alzheimer's disease (AD), resulting in progressive cognitive decline. Although tau-PET imaging is a direct biomarker of tau pathology, it is costly, carries radiation risks, and is not widely accessible. Resting-state functional MRI (rs-fMRI) complexity-an entropy-based measure of BOLD signal variation-has been proposed as a non-invasive surrogate biomarker of early neuronal dysfunction associated with tau pathology.
View Article and Find Full Text PDFDevelopment of Effective Connectome from Infancy to Adolescence.
Med Image Comput Comput Assist Interv
October 2024
Department of Radiology and Biomedical Research Imaging Center (BRIC), University of North Carolina at Chapel Hill, Chapel Hill, USA.
Delineating the normative developmental profile of functional connectome is important for both standardized assessment of individual growth and early detection of diseases. However, functional connectome has been mostly studied using functional connectivity (FC), where undirected connectivity strengths are estimated from statistical correlation of resting-state functional MRI (rs-fMRI) signals. To address this limitation, we applied regression dynamic causal modeling (rDCM) to delineate the developmental trajectories of effective connectivity (EC), the directed causal influence among neuronal populations, in whole-brain networks from infancy to adolescence (0-22 years old) based on high-quality rs-fMRI data from Baby Connectome Project (BCP) and Human Connectome Project Development (HCP-D).
View Article and Find Full Text PDFThe neural basis of the insight memory advantage.
Trends Cogn Sci
January 2025
Department of Psychology, Humboldt University Berlin, Berlin, Germany; Center for Cognitive Neuroscience, Duke University, Durham, NC 27708, USA.
Creative problem solving and memory are inherently intertwined: memory accesses existing knowledge while creativity enhances it. Recent studies show that insights often accompanying creative solutions enhance long-term memory. This insight memory advantage (IMA) is explained by the 'insight as prediction error (PE)' hypothesis which states that insights arise from PEs updating predictive solution models and thereby enhancing memory.
View Article and Find Full Text PDFNoninvasive Anemia Detection and Hemoglobin Estimation from Retinal Images Using Deep Learning: A Scalable Solution for Resource-Limited Settings.
Transl Vis Sci Technol
January 2025
School of Optometry and Vision Science, University of New South Wales, Sydney, Australia.
Purpose: The purpose of this study was to develop and validate a deep-learning model for noninvasive anemia detection, hemoglobin (Hb) level estimation, and identification of anemia-related retinal features using fundus images.
Methods: The dataset included 2265 participants aged 40 years and above from a population-based study in South India. The dataset included ocular and systemic clinical parameters, dilated retinal fundus images, and hematological data such as complete blood counts and Hb concentration levels.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!