Filters








3,904 Hits in 5.3 sec

Quantitative Analysis of Human-Model Agreement in Visual Saliency Modeling: A Comparative Study

Ali Borji, D. N. Sihite, L. Itti
2013 IEEE Transactions on Image Processing  
Our study allows one to assess the state-of-the-art, helps organizing this rapidly growing field, and sets a unified comparison framework for gauging future efforts, similar to the PASCAL VOC challenge  ...  Visual attention is a process that enables biological and machine vision systems to select the most relevant regions from a scene.  ...  A. Settings The first step in this study was to collect saliency models. Some models were already shared online.  ... 
doi:10.1109/tip.2012.2210727 pmid:22868572 fatcat:qgw3ua3gd5ekhnv6bdk34gub6a

Mesh Saliency via Weakly Supervised Classification-for-Saliency CNN

Ran Song, Yonghuai Liu, Paul Rosin
2019 IEEE Transactions on Visualization and Computer Graphics  
Quite a few pilot studies showed that this task is difficult. In this work, we solve this problem by developing a novel network trained in a weakly supervised manner.  ...  Our Classification-for-Saliency CNN (CfS-CNN) employs a multi-view setup and contains a newly designed two-channel structure which integrates view-based features of both classification and saliency.  ...  Fig. 1 , we carry out an ablation study where we compare the CfS-CNN with its ablated version.  ... 
doi:10.1109/tvcg.2019.2928794 pmid:31329121 fatcat:qacg2u5o7vgaflf2iurexdybna

Saliency Detection on Light Field

Nianyi Li, Jinwei Ye, Yu Ji, Haibin Ling, Jingyi Yu
2017 IEEE Transactions on Pattern Analysis and Machine Intelligence  
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.  ...  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.  ...  All-focus Image Groud Truth Saliency by GBMR Our Saliency Figure 1 . Light field vs. traditional saliency detection.  ... 
doi:10.1109/tpami.2016.2610425 pmid:27654139 fatcat:or55vx6jxffa5hg4akolme73ym

Saliency Detection on Light Field

Nianyi Li, Jinwei Ye, Yu Ji, Haibin Ling, Jingyi Yu
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
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.  ...  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.  ...  All-focus Image Groud Truth Saliency by GBMR Our Saliency Figure 1 . Light field vs. traditional saliency detection.  ... 
doi:10.1109/cvpr.2014.359 dblp:conf/cvpr/LiYJLY14 fatcat:fmqz7vdc3fdpvhznpkyjvermbe

A weighted sparse coding framework for saliency detection

Nianyi Li, Bilin Sun, Jingyi Yu
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Examples include 3D data based on stereo matching and Kinect sensors and more recently 4D light field data.  ...  Specifically, we first select a group of potential foreground superpixels to build a primitive saliency dictionary.  ...  A unique feature of light field is that it enables dynamic refocusing through light field rendering.  ... 
doi:10.1109/cvpr.2015.7299158 dblp:conf/cvpr/LiSY15 fatcat:t54bvjlvkra25hkugrkms2f6ka

Glutamate in Salience Network Predicts BOLD Response in Default Mode Network During Salience Processing

Felicia von Düring, Inka Ristow, Meng Li, Dominik Denzel, Lejla Colic, Liliana Ramona Demenescu, Shijia Li, Viola Borchardt, Thomas Liebe, Matthias Vogel, Martin Walter
2019 Frontiers in Behavioral Neuroscience  
Twenty-seven healthy subjects (12♀, 15♁) provided both STEAM MRS at 7T measuring glutamate concentrations in the dACC as well as a functional magnetic resonance imaging (fMRI) task to study the influence  ...  Magnetic resonance spectroscopy (MRS) studies revealed the link between the glutamate concentration in the ACC and alterations in attentional scope.  ...  the subgenual Anterior Cingulate Cortex (sgACC) and ventral striatum (VS) (p < 0.001, k = 276), Figure 2D , dark green; for mean beta estimates from VS + sgACC regarding the respective expectancy conditions  ... 
doi:10.3389/fnbeh.2019.00232 pmid:31632250 pmcid:PMC6783560 fatcat:fjynkpml7vhlhgthcuhp3alb3y

Saliency Preservation in Low-Resolution Grayscale Images [article]

Shivanthan A.C. Yohanandan, Adrian G. Dyer, Dacheng Tao, Andy Song
2018 arXiv   pre-print
In this study, we explain the biological and computational motivation for LG, and show, through a range of human eye-tracking and computational modeling experiments, that saliency information is preserved  ...  Previous studies showed that low-resolution color and high-resolution grayscale images preserve saliency information.  ...  Previous studies used fixation maps to compare saliency similarity between images [17, 45] .  ... 
arXiv:1712.02048v3 fatcat:eoujj54nengjbbizozelvgsnou

Saliency-Based Color Accessibility

Satohiro Tajima, Kazuteru Komine
2015 IEEE Transactions on Image Processing  
We developed a method for quantifying and visualizing information loss and gain resulting from individual differences in spectral sensitivity based on visual salience.  ...  Moreover, saliency-guided image manipulations sufficiently compensated for individual differences in saliency.  ...  Quantification of saliency divergence Finally, a spatial distribution of "saliency loss and gain" was obtained by comparing the two different saliency maps (Fig. 3e ) between groups (normal vs. CD).  ... 
doi:10.1109/tip.2015.2393056 pmid:25608304 fatcat:ac6oaqzqdbgvnose3dj2nkbh54

Synergistic saliency and depth prediction for RGB-D saliency detection [article]

Yue Wang, Yuke Li, James H. Elder, Huchuan Lu, Runmin Wu, Lu Zhang
2020 arXiv   pre-print
Our approach also achieves comparable results on other popular RGB-D saliency benchmarks.  ...  Here we propose a semi-supervised system for RGB-D saliency detection that can be trained on smaller RGB-D saliency datasets without saliency ground truth, while also make effective joint use of a large  ...  NJUD [16] has 1985 images taken by a Fuji W3 stereo camera; NLPR [26] contains 1000 images constructed by Kinect; LFSD [20] has 100 images using the Lytro light field camera, STEREO [25] includes  ... 
arXiv:2007.01711v2 fatcat:7n45wsmfi5hirjkqg6arq5vzdy

Perceptive fields of saliency

F. J. A. M. Poirier, F. Gosselin, M. Arguin
2008 Journal of Vision  
Perceptual fields of contextual modulation are derived, showing increased saliency surrounding color and/or orientation changes, increased saliency for collinear and end-stopping lines, and a nonlinear  ...  These novel findings allow a revision of current models of visual saliency. In particular, we found evidence of sustained saliency.  ...  The 2D plot shows increases (green) or decreases (red) in average item saliency, compared to average saliency (black).  ... 
doi:10.1167/8.15.14 pmid:19146298 fatcat:udfe5h2aefba3pg3iuxnzxeqgi

A Neurodynamic model of Saliency prediction in V1 [article]

David Berga, Xavier Otazu
2020 arXiv   pre-print
In this work we show that a biologically plausible computational model of lateral interactions of V1 is able to simultaneously predict saliency and all the aforementioned visual processes.  ...  This can be useful for the definition of a unified architecture of the primary visual cortex.  ...  As shown in Section 3.2.4, saliency computations could be more accurately represented with a higher number of 2D Gabor/Log-Gabor filters [43] [25] [27] .  ... 
arXiv:1811.06308v8 fatcat:azwxzy3wdffctdwga77sapho74

Saliency Preservation in Low-Resolution Grayscale Images [chapter]

Shivanthan Yohanandan, Andy Song, Adrian G. Dyer, Dacheng Tao
2018 Lecture Notes in Computer Science  
In this study, we explain the biological and computational motivation for LG, and show, through a range of human eyetracking and computational modeling experiments, that saliency information is preserved  ...  Previous studies showed that low-resolution color and high-resolution grayscale images preserve saliency information.  ...  Previous studies used fixation maps to compare saliency similarity between images [14, 46] .  ... 
doi:10.1007/978-3-030-01231-1_15 fatcat:25n7cfv4mrfpbadnkbq4fjl5cu

Salience Guided Depth Calibration for Perceptually Optimized Compressive Light Field 3D Display

Shizheng Wang, Wenjuan Liao, Phil Surman, Zhigang Tu, Yuanjin Zheng, Junsong Yuan
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
2D displays.  ...  for multi-layer light field display.  ...  Salience Detection on Light Field With vs. Without Learning. Recently, several studies have developed learning methods in saliency analysis [53, 27, 21] . For example, Judd et al.  ... 
doi:10.1109/cvpr.2018.00217 dblp:conf/cvpr/WangLS0ZY18 fatcat:liqplgbeazc3va6xbgfp2o5bli

Unified Image and Video Saliency Modeling [article]

Richard Droste, Jianbo Jiao, J. Alison Noble
2020 arXiv   pre-print
While image saliency modeling is a well-studied problem and progress on benchmarks like SALICON and MIT300 is slowing, video saliency models have shown rapid gains on the recent DHF1K benchmark.  ...  5 to 20-fold smaller model size compared to all competing deep methods.  ...  Unified Image and Video Saliency Modeling Code The full code for evaluating and training the UNISAL model is available at https://github.com/rdroste/unisal.  ... 
arXiv:2003.05477v2 fatcat:mghlfa4vbfe6dmc7tf2did4wqi

The Contribution of Parietal Cortex to Visual Salience [article]

Xiaomo Chen, Marc Zirnsak, Gabriel Michael Vega, Eshan Govil, Stephen Lomber, Tirin Moore
2019 biorxiv/medrxiv   pre-print
Among the possible candidates are areas within posterior parietal cortex, which appear to be crucial in the control of visual attention and are thought to play a unique role in representing stimulus salience  ...  However, the source of the salience computation has remained elusive.  ...  Quantitative Analysis of Human-Model Agreement in Visual Saliency Modeling: A Comparative Study. IEEE Trans. Image Process. 22, 55-69 (2013).All rights reserved.  ... 
doi:10.1101/619643 fatcat:awmwz4swxrdbrdgdtozuwwkaci
« Previous Showing results 1 — 15 out of 3,904 results