Nermin Samet

I am a Research Scientist at Valeo.ai. Prior to joining Valeo.ai, I worked as a postdoctoral researcher at ENPC ParisTech, IMAGINE Research Group with Prof. Vincent Lepetit. I obtained my Ph.D. degree in 2021 from the Department of Computer Engineering at METU under supervision of Dr. Emre Akbas. My primary research interests lie in computer vision, with a focus on data-efficient learning for 3D point clouds and human pose estimation.

News

Research

You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation

@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}
}

H3WB: Human3.6M 3D WholeBody Dataset and Benchmark

@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}
}

A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation

@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}} 
}

HoughNet: Integrating near and long-range evidence for visual detection

@misc{HoughNet2021,
      title={HoughNet: Integrating near and long-range evidence for visual detection}, 
      author={Nermin Samet and Samet Hicsonmez and Emre Akbas},
      year={2021}, 
}

HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation

@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},
}

Adversarial Segmentation Loss for Sketch Colorization

@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}
  }

Reducing Label Noise in Anchor-Free Object Detection

@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},
}

HoughNet: Integrating near and long-range evidence for bottom-up object detection

@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}
}

GANILLA: Generative adversarial networks for image to illustration translation

@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}
}

Could We Create A Training Set For Image Captioning Using Automatic Translation?

@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}
}

Ground-nesting Insects could use Visual Tracking for Monitoring Nest Position during Learning Flights

@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}
}

Inspired from Jon Barron's website