Filters








10 Hits in 2.2 sec

PathGAN: Visual Scanpath Prediction with Generative Adversarial Networks [chapter]

Marc Assens, Xavier Giro-i-Nieto, Kevin McGuinness, Noel E. O'Connor
<span title="">2019</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
We introduce PathGAN, a deep neural network for visual scanpath prediction trained on adversarial examples.  ...  A visual scanpath is defined as the sequence of fixation points over an image defined by a human observer with its gaze. PathGAN is composed of two parts, the generator and the discriminator.  ...  Section 2 reviews the state-of-the-art models for visual saliency prediction and recent advances on conditional adversarial networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-11021-5_25">doi:10.1007/978-3-030-11021-5_25</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5bthnxxzybb6nbsj4sbfem74pu">fatcat:5bthnxxzybb6nbsj4sbfem74pu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190430185703/http://doras.dcu.ie/22730/1/assens-2018-pathgan.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c8/66/c866091963b1094659fd7f013687671dc921c788.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-11021-5_25"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

SALYPATH: A Deep-Based Architecture for visual attention prediction [article]

Mohamed Amine Kerkouri, Marouane Tliba, Aladine Chetouani, Rachid Harba
<span title="2021-06-29">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The idea is predict the scanpath by exploiting the capacity of a deep-based model to predict the saliency. The proposed method was evaluated through 2 well-known datasets.  ...  In this paper, we propose an end-to-end deep-based method, so-called SALYPATH (SALiencY and scanPATH), that efficiently predicts the scanpath of an image through features of a saliency model.  ...  The authors later proposed a saliency model, called PathGan [24] , that predicts scanpath by using LSTM layers and a VGG network with adversarial training.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.00559v1">arXiv:2107.00559v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/edspx6qbjbesfav3rvs544wab4">fatcat:edspx6qbjbesfav3rvs544wab4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210707015110/https://arxiv.org/pdf/2107.00559v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/52/e2/52e24a3a8288499093dac27846eb1f9558b4fc21.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.00559v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Simple and efficient deep Scanpath Prediction [article]

Mohamed Amine Kerkouri, Aladine Chetouani
<span title="2021-12-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Visual scanpath is the sequence of fixation points that the human gaze travels while observing an image, and its prediction helps in modeling the visual attention of an image.  ...  We experiment how well these models can predict the scanpaths on 2 datasets.  ...  Proceedings of the IEEE International Conference on Computer Vision Workshops. 2017. [24] Assens, Marc, et al. ”PathGAN: visual scanpath prediction with gen- erative adversarial networks.”  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.04610v1">arXiv:2112.04610v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xc7qlk4odjc6fnjvg7dgsqxzbu">fatcat:xc7qlk4odjc6fnjvg7dgsqxzbu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211211035112/https://arxiv.org/pdf/2112.04610v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4b/4b/4b4b145fbbebddaa57f76876e5203ec592ca9bf4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.04610v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

SalyPath360: Saliency and scanpath prediction framework for omnidirectional images

Kerkouri Mohamed Amine, Tliba Marouane, Chetouani Aladine, Sayeh Mohamed
<span title="2022-01-16">2022</span> <i title="Society for Imaging Science &amp; Technology"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/sajjfb6z3be2xbfjs4d2afwzyi" style="color: black;">IS&amp;T International Symposium on Electronic Imaging Science and Technology</a> </i> &nbsp;
This paper introduces a new framework to predict the visual attention of omnidirectional images.  ...  The framework implements a fully encoder-decoder convolutional neural network augmented by an attention module to generate representative saliency maps.  ...  In [4] , the authors proposed a deep neural network, that uses an encoder-decoder network and Long Short Term Memory (LSTM) layers to generate scanpaths, combined with adversarial training by Generative  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2352/ei.2022.34.11.hvei-168">doi:10.2352/ei.2022.34.11.hvei-168</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6txgk4v5yrbnvjvqlw3wng2s4e">fatcat:6txgk4v5yrbnvjvqlw3wng2s4e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220630073952/https://library.imaging.org/admin/apis/public/api/sandbox/website/downloadArticle/ei/34/11/HVEI-168" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cd/b9/cdb916f3d89fa8893dd89b07db27503cf1b9c9a4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2352/ei.2022.34.11.hvei-168"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

A simple and efficient deep scanpath prediction

Kerkouri Mohamed A., Chetouani Aladine
<span title="2022-01-16">2022</span> <i title="Society for Imaging Science &amp; Technology"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/sajjfb6z3be2xbfjs4d2afwzyi" style="color: black;">IS&amp;T International Symposium on Electronic Imaging Science and Technology</a> </i> &nbsp;
We experiment with how well these models can predict the scanpaths on 2 datasets.  ...  Visual scanpath is the sequence of fixation points that the human gaze travels while observing an image, and its prediction helps in modeling the visual attention of an image.  ...  [19] introduced the use of generative modeling and adversarial learning for the proposed SalGan Model, by using a deep convolutional Generative Adversarial Network (GAN). While Cornea et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2352/ei.2022.34.11.hvei-188">doi:10.2352/ei.2022.34.11.hvei-188</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/maor2ql45bgidp2xw6ba2m7qie">fatcat:maor2ql45bgidp2xw6ba2m7qie</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220409001044/https://library.imaging.org/admin/apis/public/api/sandbox/website/downloadArticle/ei/34/11/HVEI-188" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e6/e8/e6e8239923ceb67930d3e55c8970b308e9a4e59d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2352/ei.2022.34.11.hvei-188"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Scanpath Prediction on Information Visualisations [article]

Yao Wang, Mihai Bâce, Andreas Bulling
<span title="2021-12-04">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose Unified Model of Saliency and Scanpaths (UMSS) -- a model that learns to predict visual saliency and scanpaths (i.e. sequences of eye fixations) on information visualisations.  ...  Although scanpaths provide rich information about the importance of different visualisation elements during the visual exploration process, prior work has been limited to predicting aggregated attention  ...  O’Connor, “Pathgan: visual scanpath prediction with generative adversarial networks,” in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 0–0. [4] W. Bao and Z.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.02340v1">arXiv:2112.02340v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wttsjupdoneankubda7wt4iq3q">fatcat:wttsjupdoneankubda7wt4iq3q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211208163958/https://arxiv.org/pdf/2112.02340v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2f/59/2f595d408ecedc2ddd2780ce4af3b66380e04306.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.02340v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgery [article]

Mobarakol Islam, Vibashan VS, Chwee Ming Lim, Hongliang Ren
<span title="2021-12-10">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We generate the task-aware saliency maps and scanpath of the instruments on the dataset of the MICCAI 2017 robotic instrument segmentation challenge.  ...  Incorporating cognitive ability to automate the camera control enables the surgeon to concentrate more on dealing with surgical instruments.  ...  PathGAN [6] consists of an end-to-end model capable of predicting scanpaths on ordinary and omnidirectional images using the framework of conditional adversarial networks [32] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.08189v1">arXiv:2112.08189v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ck7rypz2lnfbplc4z3kejcjzae">fatcat:ck7rypz2lnfbplc4z3kejcjzae</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211217142042/https://arxiv.org/pdf/2112.08189v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/52/94/5294ced261c35b3e76fc09c800e8d5142fe619cc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.08189v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Variational Autoencoder for Image-Based Augmentation of Eye-Tracking Data

Mahmoud Elbattah, Colm Loughnane, Jean-Luc Guérin, Romuald Carette, Federica Cilia, Gilles Dequen
<span title="2021-05-03">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/au3ye363lzbdroopx7rzfyv63m" style="color: black;">Journal of Imaging</a> </i> &nbsp;
More specifically, a VAE model is trained to generate an image-based representation of the eye-tracking output, so-called scanpaths.  ...  Overall, our results validate that the VAE model could generate a plausible output from a limited dataset.  ...  On the basis of adversarial learning, the PathGAN framework presented an end-to-end model for predicting the visual scanpath.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/jimaging7050083">doi:10.3390/jimaging7050083</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/34460679">pmid:34460679</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8321343/">pmcid:PMC8321343</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bihahevljrat5gaddcwgjk3tlq">fatcat:bihahevljrat5gaddcwgjk3tlq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210717025714/https://res.mdpi.com/d_attachment/jimaging/jimaging-07-00083/article_deploy/jimaging-07-00083.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7b/db/7bdbc5b84d8617b7213b492707a1f63a038939c7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/jimaging7050083"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8321343" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

State-of-the-Art in Human Scanpath Prediction [article]

Matthias Kümmerer, Matthias Bethge
<span title="2021-10-04">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
scanpath prediction.  ...  This makes model evaluation closely aligned with the biological processes thought to underly scanpath generation and allows to apply established saliency metrics like AUC and NSS in an intuitive and interpretable  ...  In order to select a next fixation, the model samples multiple candidates from a spatial distribution and chooses the sample with highest probability.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.12239v2">arXiv:2102.12239v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/74vimv7s2nh4dhembhlzfmz4qy">fatcat:74vimv7s2nh4dhembhlzfmz4qy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211006025107/https://arxiv.org/pdf/2102.12239v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b5/58/b558fdbdf91abbb145579aa1ed89d8decd2e6b30.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.12239v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A STOCHASTIC FORAGING MODEL OF ATTENTIVE EYE GUIDANCE ON DYNAMIC STIMULI

ALESSANDRO D'AMELIO
<span title="2021-03-22">2021</span>
of predicting attention allocation on a visual stimuli has started to catch the interest of the computer vision and pattern recognition community, pushed by the fast growing number of possible applications  ...  Moreover, the vast majority of the proposed models are only able to deal with static stimuli (images), with few notable exceptions.  ...  More recently, solutions relying on deep networks have been proposed; Assens et al. (2018a) proposed PathGAN, a deep neural network for visual scanpath prediction trained on adversarial examples.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.13130/d-amelio-alessandro_phd2021-03-22">doi:10.13130/d-amelio-alessandro_phd2021-03-22</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7hbrsmolmvbrzlrtdcd5f6cj6a">fatcat:7hbrsmolmvbrzlrtdcd5f6cj6a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210331030451/https://air.unimi.it/retrieve/handle/2434/816678/1710072/phd_unimi_R11866.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/83/66/83666714ddc9791563ef1f34d4fbc09971504281.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.13130/d-amelio-alessandro_phd2021-03-22"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>