Nermin Samet

<!DOCTYPE HTML> <html lang="en"> <head> <title>Nermin Samet</title> <meta content="text/html; charset=utf-8" http-equiv="Content-Type"> <meta name="author" content="Nermin Samet" /> <meta name="viewport" content="width=device-width, initial-scale=1"> <link rel="stylesheet" type="text/css" href="/styles/style.css" /> <link rel="canonical" href="https://nerminsamet.github.io/"> <link href="https://fonts.googleapis.com/css?family=Lato:400,700,400italic,700italic" rel="stylesheet" type="text/css"> <link href="/styles/all.min.css" rel="stylesheet"> <link rel="stylesheet" href="/styles/academicons.min.css"> <link rel="icon" type="image/jpg" href="images/nazar-amulet.svg"/> <script type="text/javascript" src="/js/toggleBib.js"></script> </head> <body> <table style="width:100%;max-width:1000px;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;"> <tr style="padding:0px"> <td style="padding:0px"> <table style="width:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;"> <tr style="padding:0px"> <td style="padding:2.5%;width:20%;max-width:20%"> <a href="https://giddyyupp.github.io/" target="_blank"> <img style="width:100%;max-width:100%;border-radius: 10%;" alt="profile photo" src="images/profile.jpg"> </a> </td> <td style="padding:2.5%;width:60%;vertical-align:middle"> <h1> Nermin Samet </h1> <p> I am a Research Scientist at <a href="https://valeoai.github.io/publications/" target="_blank"> Valeo.ai</a>. Prior to joining Valeo.ai, I worked as a postdoctoral researcher at <a href="https://www.ecoledesponts.fr/" target="_blank"> ENPC ParisTech</a>, <a href="https://imagine-lab.enpc.fr/" target="_blank"> IMAGINE Research Group</a> with <a href="https://vincentlepetit.github.io/" target="_blank"> Prof. Vincent Lepetit</a>. I obtained my Ph.D. degree in 2021 from the <a href="http://ceng.metu.edu.tr/" target="_blank"> Department of Computer Engineering</a> at <a href="http://www.metu.edu.tr/" target="_blank">METU</a> under supervision of <a href="http://user.ceng.metu.edu.tr/~emre/" target="_blank">Dr. Emre Akbas</a>. My primary research interests lie in computer vision, with a focus on data-efficient learning for 3D point clouds and human pose estimation. </p> <p style="text-align:center"> <div class="contact-buttons"> <a href="mailto:nermin.samet@metu.edu.tr" target="_blank"><i class="far fa-envelope fa-2x"></i></a> <a href="https://github.com/nerminsamet" target="_blank"><i class="fab fa-github fa-2x"></i></a> <a href="https://scholar.google.com/citations?user=kEVeHU0AAAAJ" target="_blank"><i class="ai ai-google-scholar fa-2x"></i></a> <a href="https://www.linkedin.com/in/nermin-samet-a70007156" target="_blank"><i class="fab fa-linkedin-in fa-2x"></i></a> <a href="https://twitter.com/nemka_" target="_blank"><i class="fab fa-twitter fa-2x"></i></a> <a href="https://www.youtube.com/user/nemka911/videos" target="_blank"><i class="fab fa-youtube fa-2x"></i></a>  </div> </p> </td> </tr> </table> <hr> <table style="width:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;"> <tr> <td style="padding:2.5% 2.5% 0% 2.5%;width:100%;vertical-align:middle"> <h2><b>News</b></h2> </td> </tr> </table> <div class="timeline"> <div class="timeline-news"> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #A569BD;"></div> <span style="background-color: #A569BD;">Oct 2023</span> <p class="timeline-title">I received the "METU Thesis of the Year Award" given by the Graduate School of Natural and Applied Sciences!</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #A569BD;"></div> <span style="background-color: #A569BD;">Jul 2023</span> <p class="timeline-title"><a href='https://arxiv.org/abs/2304.11762' target='_blank'>SeedAL</a> and <a href='https://arxiv.org/abs/2211.15692' target='_blank'>H3WB</a> got accepted to the IEEE International Conference on Computer Vision (ICCV) 2023!</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #A569BD;"></div> <span style="background-color: #A569BD;">May 2023</span> <p class="timeline-title">Our paper entitled “You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation” is now available on <a href='https://arxiv.org/abs/2304.11762' target='_blank'>arXiv</a>. Code is available at <a href='https://github.com/nerminsamet/seedal' target='_blank'>here</a>.</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #b5e7a0;"></div> <span style="background-color: #b5e7a0;">Dec 2022</span> <p class="timeline-title">Our paper entitled “H3WB: Human3.6M 3D WholeBody Dataset and Benchmark” is now available on <a href='https://arxiv.org/abs/2211.15692' target='_blank'>arXiv</a>. H3WB Dataset and benchmark are available <a href='https://github.com/wholebody3d/wholebody3d' target='_blank'>here</a>.</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #b5e7a0;"></div> <span style="background-color: #b5e7a0;">Oct 2022</span> <p class="timeline-title">Our paper entitled <a href='https://arxiv.org/abs/2209.09341' target='_blank'>“A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation”</a> is accepted to the IEEE Winter Conference on Applications of Computer Vision (WACV).</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #b5e7a0;"></div> <span style="background-color: #b5e7a0;">Aug 2022</span> <p class="timeline-title">Our extended work on <a href='https://arxiv.org/abs/2104.06773' target='_blank'>HoughNet</a> is accepted to the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #6495ED;"></div> <span style="background-color: #6495ED;">Nov 2021</span> <p class="timeline-title">I am among the <a href='https://www.bmvc2021-virtualconference.com/people/reviewers/' target='_blank'> outstanding BMVC2021 reviewers</a>!</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #6495ED;"></div> <span style="background-color: #6495ED;">Nov 2021</span> <p class="timeline-title">I started my Postdoc at <a href='https://www.ecoledesponts.fr/' target='_blank'>École des Ponts (ENPC) ParisTech</a>, <a href='https://imagine-lab.enpc.fr/' target='_blank'>IMAGINE Research Group</a>.</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #6495ED;"></div> <span style="background-color: #6495ED;">Oct 2021</span> <p class="timeline-title">I will be co-organizing the <a href='https://sites.google.com/view/wicv/' target='_blank'>Women in Computer Vision Workshop</a> at <a href='https://cvpr2022.thecvf.com/' target='_blank'>CVPR 2022</a>.</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #6495ED;"></div> <span style="background-color: #6495ED;">Sep 2021</span> <p class="timeline-title">I successfully defended my <a href='https://open.metu.edu.tr/handle/11511/92178' target='_blank'>Ph.D thesis</a>. Here is <a href='https://drive.google.com/file/d/14I1a4VFekvDoVgnSG7USU6NlL-Prr_0Z/view?usp=sharing' target='_blank'>my acedemic family tree</a> (<a href='https://www.genealogy.math.ndsu.nodak.edu/' target='_blank'>source</a>).</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #6495ED;"></div> <span style="background-color: #6495ED;">Sep 2021</span> <p class="timeline-title">HPRNet is accepted to Image and Vision Computing: <a href='https://www.sciencedirect.com/science/article/pii/S0262885621001906?via%3Dihub' target='_blank'>publisher's page</a> </p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #6495ED;"></div> <span style="background-color: #6495ED;">Jun 2021</span> <p class="timeline-title">Our paper entitled “HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation” is now available on <a href='https://arxiv.org/abs/2106.04269' target='_blank'>arXiv</a>.</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #6495ED;"></div> <span style="background-color: #6495ED;">May 2021</span> <p class="timeline-title">Our paper “Adversarial Segmentation Loss for Sketch Colorization” is accepted to the International Conference on Image Processing (ICIP).</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #6495ED;"></div> <span style="background-color: #6495ED;">Apr 2021</span> <p class="timeline-title">Our extended work on HoughNet, “HoughNet: Integrating near and long-range evidence for visual detection” is now available on <a href='https://arxiv.org/abs/2104.06773' target='_blank'>arXiv</a>.</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #6495ED;"></div> <span style="background-color: #6495ED;">Feb 2021</span> <p class="timeline-title">Our paper entitled “Adversarial Segmentation Loss for Sketch Colorization” is now available on <a href='https://arxiv.org/abs/2102.06192' target='_blank'>arXiv</a>.</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #ff5733;"></div> <span style="background-color: #ff5733;">Oct 2020</span> <p class="timeline-title">I will be co-organizing the <a href='https://sites.google.com/view/wicvcvpr2021/home' target='_blank'>Women in Computer Vision Workshop</a> at <a href='http://cvpr2021.thecvf.com/' target='_blank'>CVPR 2021</a>.</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #ff5733;"></div> <span style="background-color: #ff5733;">Sep 2020</span> <p class="timeline-title">Our work <a href='https://arxiv.org/abs/2002.05638' target='_blank'>GANILLA</a> has been featured in “<a href='https://blog.deeplearning.ai/blog/the-batch-gan-special-issue-ian-goodfellow-for-real-detecting-fakes-including-minorities-synthesizing-training-data-applying-virtual-make-up' target='_blank'>The Batch</a>”, a new weekly newsletter from deeplearning.ai. </p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #ff5733;"></div> <span style="background-color: #ff5733;">Aug 2020</span> <p class="timeline-title">Our paper entitled “<a href='https://arxiv.org/abs/2008.01167' target='_blank'>Reducing Label Noise in Anchor-Free Object Detection</a>” is accepted to the British Machine Vision Conference (BMVC).</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #ff5733;"></div> <span style="background-color: #ff5733;">Jun 2020</span> <p class="timeline-title">Our paper entitled “<a href='https://arxiv.org/abs/2007.02355' target='_blank'>HoughNet: Integrating near and long-range evidence for bottom-up object detection</a>” is accepted to the European Conference on Computer Vision (ECCV).</p> </div> </div> <div class="timeline-item"> <div class="timeline-date"> <div class="timeline-dot" style="background-color: #ff5733;"></div> <span style="background-color: #ff5733;">Jan 2020</span> <p class="timeline-title">Our paper entitled “<a href='https://arxiv.org/abs/2002.05638' target='_blank'>GANILLA: Generative adversarial networks for image to illustration translation</a>” is accepted to Image and Vision Computing.</p> </div> </div> </div> </div> <hr> <table style="width:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;"> <tr> <td style="padding:2.5% 2.5% 0% 2.5%;width:100%;vertical-align:middle"> <h2><b>Research</b></h2> </td> </tr> </table> <table style="width:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;"> <tr> <td style="padding:2.5%;width:75%;vertical-align:middle"> <h3>You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation</h3> <br> <strong>Nermin Samet</strong>, Oriane Siméoni, Gilles Puy, Georgy Ponimatkin, Renaud Marlet, Vincent Lepetit <br> <em>IEEE International Conference on Computer Vision (ICCV)</em> 2023<br> <div class="research-buttons"> <a href="https://arxiv.org/abs/2304.11762" target="_blank"><button type="button" class="research-button"><i class="ai ai-arxiv fa-lg"></i><span>arXiv</span></button></a> <a href="https://github.com/nerminsamet/seedal" target="_blank"><button type="button" class="research-button"><i class="fab fa-github fa-lg"></i><span>Code</span></button></a> <a href="javascript:toggleBib('bib/seedal.bib')"><button type="button" class="research-button"><span>BibTeX</span></button></a> </div> <pre id="bib/seedal.bib" style="display: none;">@article{seedal, title={You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation}, author={Nermin Samet, Oriane Siméoni, Gilles Puy, Georgy Ponimatkin, Renaud Marlet, Vincent Lepetit}, booktitle={IEEE International Conference on Computer Vision (ICCV)}, year={2023} } </pre> </td> </tr> <tr> <td style="padding:2.5%;width:75%;vertical-align:middle"> <h3>H3WB: Human3.6M 3D WholeBody Dataset and Benchmark</h3> <br> Yue Zhu, <strong>Nermin Samet</strong>, David Picard <br> <em>IEEE International Conference on Computer Vision (ICCV)</em> 2023<br> <div class="research-buttons"> <a href="https://arxiv.org/abs/2211.15692" target="_blank"><button type="button" class="research-button"><i class="ai ai-arxiv fa-lg"></i><span>arXiv</span></button></a> <a href="https://github.com/wholebody3d/wholebody3d" target="_blank"><button type="button" class="research-button"><i class="fab fa-github fa-lg"></i><span>Code</span></button></a> <a href="javascript:toggleBib('bib/h3wb.bib')"><button type="button" class="research-button"><span>BibTeX</span></button></a> </div> <pre id="bib/h3wb.bib" style="display: none;">@article{h3wb, title={H3WB: Human3.6M 3D WholeBody Dataset and benchmark}, author={Yue Zhu, Nermin Samet, David Picard}, booktitle={IEEE International Conference on Computer Vision (ICCV)}, year={2023} } </pre> </td> </tr> <tr> <td style="padding:2.5%;width:75%;vertical-align:middle"> <h3>A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation</h3> <br> Georgy Ponimatkin, <strong>Nermin Samet</strong>, Yang Xiao, Yuming Du, Renaud Marlet, Vincent Lepetit <br> <em>IEEE Winter Conference on Applications of Computer Vision (WACV)</em> 2022<br> <div class="research-buttons"> <a href="https://arxiv.org/abs/2209.09341" target="_blank"><button type="button" class="research-button"><i class="ai ai-arxiv fa-lg"></i><span>arXiv</span></button></a> <a href="https://arxiv.org/abs/2209.09341" target="_blank"><button type="button" class="research-button"><i class="far fa-file-pdf fa-lg"></i><span>Paper</span></button></a> <a href="https://github.com/ponimatkin/ssl-vos" target="_blank"><button type="button" class="research-button"><i class="fab fa-github fa-lg"></i><span>Code</span></button></a> <a href="javascript:toggleBib('bib/wacv23.bib')"><button type="button" class="research-button"><span>BibTeX</span></button></a> </div> <pre id="bib/wacv23.bib" style="display: none;">@inproceedings{ponimatkin2023sslvos, title= {A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation}, author={G. {Ponimatkin} and N. {Samet} and Y. {Xiao} and Y. {Du} and R. {Marlet} and V. {Lepetit}}, booktitle={Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV)}, year={2023}} } </pre> </td> </tr> <tr> <td style="padding:2.5%;width:75%;vertical-align:middle"> <h3>HoughNet: Integrating near and long-range evidence for visual detection</h3> <br> <strong>Nermin Samet</strong>, Samet Hicsonmez, Emre Akbas <br> <em>IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)</em> 2022<br> <div class="research-buttons"> <a href="https://arxiv.org/abs/2104.06773" target="_blank"><button type="button" class="research-button"><i class="ai ai-arxiv fa-lg"></i><span>arXiv</span></button></a> <a href="https://ieeexplore.ieee.org/document/9864076" target="_blank"><button type="button" class="research-button"><i class="far fa-file-pdf fa-lg"></i><span>Paper</span></button></a> <a href="https://github.com/nerminsamet/houghnet" target="_blank"><button type="button" class="research-button"><i class="fab fa-github fa-lg"></i><span>Code</span></button></a> <a href="javascript:toggleBib('bib/extendedhoughnet.bib')"><button type="button" class="research-button"><span>BibTeX</span></button></a> </div> <pre id="bib/extendedhoughnet.bib" style="display: none;">@misc{HoughNet2021, title={HoughNet: Integrating near and long-range evidence for visual detection}, author={Nermin Samet and Samet Hicsonmez and Emre Akbas}, year={2021}, } </pre> </td> </tr> <tr> <td style="padding:2.5%;width:75%;vertical-align:middle"> <h3>HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation</h3> <br> <strong>Nermin Samet</strong>, Emre Akbas <br> <em>Image and Vision Computing (IMAVIS)</em> 2021<br> <div class="research-buttons"> <a href="https://arxiv.org/abs/2106.04269" target="_blank"><button type="button" class="research-button"><i class="ai ai-arxiv fa-lg"></i><span>arXiv</span></button></a> <a href="https://www.sciencedirect.com/science/article/pii/S0262885621001906?via%3Dihub" target="_blank"><button type="button" class="research-button"><i class="far fa-file-pdf fa-lg"></i><span>Paper</span></button></a> <a href="https://github.com/nerminsamet/HPRNet" target="_blank"><button type="button" class="research-button"><i class="fab fa-github fa-lg"></i><span>Code</span></button></a> <a href="javascript:toggleBib('bib/hprnet.bib')"><button type="button" class="research-button"><span>BibTeX</span></button></a> </div> <pre id="bib/hprnet.bib" style="display: none;">@article{samet2021_hprnet, title = {HPRNet: Hierarchical point regression for whole-body human pose estimation}, journal = {Image and Vision Computing}, pages = {104285}, year = {2021}, issn = {0262-8856}, doi = {https://doi.org/10.1016/j.imavis.2021.104285}, author = {Nermin Samet and Emre Akbas}, } </pre> </td> </tr> <tr> <td style="padding:2.5%;width:75%;vertical-align:middle"> <h3>Adversarial Segmentation Loss for Sketch Colorization</h3> <br> Samet Hicsonmez, <strong>Nermin Samet</strong>, Emre Akbas, Pinar Duygulu <br> <em>International Conference on Image Processing (ICIP)</em> 2021<br> <div class="research-buttons"> <a href="https://arxiv.org/abs/2102.06192" target="_blank"><button type="button" class="research-button"><i class="ai ai-arxiv fa-lg"></i><span>arXiv</span></button></a> <a href="https://ieeexplore.ieee.org/document/9506637" target="_blank"><button type="button" class="research-button"><i class="far fa-file-pdf fa-lg"></i><span>Paper</span></button></a> <a href="https://github.com/giddyyupp/AdvSegLoss" target="_blank"><button type="button" class="research-button"><i class="fab fa-github fa-lg"></i><span>Code</span></button></a> <a href="javascript:toggleBib('bib/advsegloss.bib')"><button type="button" class="research-button"><span>BibTeX</span></button></a> </div> <pre id="bib/advsegloss.bib" style="display: none;">@INPROCEEDINGS{hicsonmez2021_advseg, author={Hicsonmez, Samet and Samet, Nermin and Akbas, Emre and Duygulu, Pinar}, booktitle={2021 IEEE International Conference on Image Processing (ICIP)}, title={Adversarial Segmentation Loss For Sketch Colorization}, year={2021}, pages={2403-2407}, doi={10.1109/ICIP42928.2021.9506637} } </pre> </td> </tr> <tr> <td style="padding:2.5%;width:75%;vertical-align:middle"> <h3>Reducing Label Noise in Anchor-Free Object Detection</h3> <br> <strong>Nermin Samet</strong>, Samet Hicsonmez, Emre Akbas <br> <em>British Machine Vision Conference (BMVC)</em> 2020<br> <div class="research-buttons"> <a href="https://arxiv.org/abs/2008.01167" target="_blank"><button type="button" class="research-button"><i class="ai ai-arxiv fa-lg"></i><span>arXiv</span></button></a> <a href="https://github.com/nerminsamet/ppdet" target="_blank"><button type="button" class="research-button"><i class="fab fa-github fa-lg"></i><span>Code</span></button></a> <a href="javascript:toggleBib('bib/ppdet.bib')"><button type="button" class="research-button"><span>BibTeX</span></button></a> </div> <pre id="bib/ppdet.bib" style="display: none;">@inproceedings{PPDet, author = {Nermin Samet and Samet Hicsonmez and Emre Akbas}, title = {Reducing {L}abel {N}oise in {A}nchor-{F}ree {O}bject {D}etection}, booktitle = {British Machine Vision Conference (BMVC)}, year = {2020}, } </pre> </td> </tr> <tr> <td style="padding:2.5%;width:75%;vertical-align:middle"> <h3>HoughNet: Integrating near and long-range evidence for bottom-up object detection</h3> <br> <strong>Nermin Samet</strong>, Samet Hicsonmez, Emre Akbas <br> <em>European Conference on Computer Vision (ECCV)</em> 2020<br> <div class="research-buttons"> <a href="https://arxiv.org/abs/2007.02355" target="_blank"><button type="button" class="research-button"><i class="ai ai-arxiv fa-lg"></i><span>arXiv</span></button></a> <a href="https://link.springer.com/chapter/10.1007/978-3-030-58595-2_25" target="_blank"><button type="button" class="research-button"><i class="far fa-file-pdf fa-lg"></i><span>Paper</span></button></a> <a href="https://github.com/nerminsamet/houghnet" target="_blank"><button type="button" class="research-button"><i class="fab fa-github fa-lg"></i><span>Code</span></button></a> <a href="https://www.youtube.com/watch?v=u8O3pk-v5Us" target="_blank"><button type="button" class="research-button"><i class="fas fa-video fa-lg"></i><span>Video</span></button></a> <a href="javascript:toggleBib('bib/houghnet.bib')"><button type="button" class="research-button"><span>BibTeX</span></button></a> </div> <pre id="bib/houghnet.bib" style="display: none;">@inproceedings{samet2020houghnet, title={HoughNet: Integrating near and long-range evidence for bottom-up object detection}, author={Samet, Nermin and Hicsonmez, Samet and Akbas, Emre}, booktitle={European Conference on Computer Vision}, pages={406--423}, year={2020}, organization={Springer} } </pre> </td> </tr> <tr> <td style="padding:2.5%;width:75%;vertical-align:middle"> <h3>GANILLA: Generative adversarial networks for image to illustration translation</h3> <br> Samet Hicsonmez, <strong>Nermin Samet</strong>, Emre Akbas, Pinar Duygulu <br> <em>Image and Vision Computing (IMAVIS)</em> 2020<br> <div class="research-buttons"> <a href="https://arxiv.org/abs/2002.05638" target="_blank"><button type="button" class="research-button"><i class="ai ai-arxiv fa-lg"></i><span>arXiv</span></button></a> <a href="https://www.sciencedirect.com/science/article/pii/S0262885620300184" target="_blank"><button type="button" class="research-button"><i class="far fa-file-pdf fa-lg"></i><span>Paper</span></button></a> <a href="https://github.com/giddyyupp/ganilla" target="_blank"><button type="button" class="research-button"><i class="fab fa-github fa-lg"></i><span>Code</span></button></a> <a href="https://www.youtube.com/watch?v=-IbNmc2mTz4" target="_blank"><button type="button" class="research-button"><i class="fas fa-video fa-lg"></i><span>Video</span></button></a> <a href="javascript:toggleBib('bib/ganilla.bib')"><button type="button" class="research-button"><span>BibTeX</span></button></a> </div> <pre id="bib/ganilla.bib" style="display: none;">@article{hicsonmez2020ganilla, title={GANILLA: Generative adversarial networks for image to illustration translation}, author={Hicsonmez, Samet and Samet, Nermin and Akbas, Emre and Duygulu, Pinar}, journal={Image and Vision Computing}, volume={95}, pages={103886}, year={2020}, publisher={Elsevier} } </pre> </td> </tr> <tr> <td style="padding:2.5%;width:75%;vertical-align:middle"> <h3>Could We Create A Training Set For Image Captioning Using Automatic Translation?</h3> <br> <strong>Nermin Samet</strong>, Samet Hicsonmez, Pinar Duygulu, Emre Akbas <br> <em>Signal Processing and Communications Applications Conference (SIU)</em> 2017<br> <div class="research-buttons"> <a href="https://ieeexplore.ieee.org/abstract/document/7960638" target="_blank"><button type="button" class="research-button"><i class="far fa-file-pdf fa-lg"></i><span>Paper</span></button></a> <a href="https://github.com/giddyyupp/turkish-image-captioning" target="_blank"><button type="button" class="research-button"><i class="fab fa-github fa-lg"></i><span>Code</span></button></a> <a href="javascript:toggleBib('bib/turkishcapt.bib')"><button type="button" class="research-button"><span>BibTeX</span></button></a> </div> <pre id="bib/turkishcapt.bib" style="display: none;">@inproceedings{samet2017captioning, title = {Could we create a training set for image captioning using automatic translation?}, author = {Nermin Samet and Samet Hicsonmez and Pinar Duygulu and Emre Akbas}, booktitle = {25th Signal Processing and Communications Applications Conference, {SIU} 2017, Antalya, Turkey, May 15-18, 2017}, pages = {1--4}, year = {2017}, organization={IEEE} } </pre> </td> </tr> <tr> <td style="padding:2.5%;width:75%;vertical-align:middle"> <h3>Ground-nesting Insects could use Visual Tracking for Monitoring Nest Position during Learning Flights</h3> <br> <strong>Nermin Samet</strong>, Jochen Zeil, Elmar Mair, Norbert Boeddeker, Wolfgang Stuerzl <br> <em>International Conference on Simulation of Adaptive Behavior (SAB)</em> 2014, Best Paper Finalist<br> <div class="research-buttons"> <a href="https://link.springer.com/chapter/10.1007/978-3-319-08864-8_11" target="_blank"><button type="button" class="research-button"><i class="far fa-file-pdf fa-lg"></i><span>Paper</span></button></a> <a href="javascript:toggleBib('bib/insects.bib')"><button type="button" class="research-button"><span>BibTeX</span></button></a> </div> <pre id="bib/insects.bib" style="display: none;">@inproceedings{samet2014ground, title={Ground-nesting insects could use visual tracking for monitoring nest position during learning flights}, author={Samet, Nermin and Zeil, Jochen and Mair, Elmar and Boeddeker, Norbert and St{\"u}rzl, Wolfgang}, booktitle={International Conference on Simulation of Adaptive Behavior}, pages={108--120}, year={2014}, organization={Springer International Publishing} } </pre> </td> </tr> </table> <table style="width:100%;border:0px;border-spacing:0px;border-collapse:separate;margin-right:auto;margin-left:auto;"> <tr> <td style="padding:0px"> <br> <p style="text-align:center;font-size:small;"> Inspired from <a style="font-size:small;" href="https://jonbarron.info">Jon Barron's website</a> </p> </td> </tr> </table> </td> </tr> </table> </body> </html>

CINXE.COM

Nermin Samet