profile photo

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

Oct 2023

I received the "METU Thesis of the Year Award" given by the Graduate School of Natural and Applied Sciences!

Jul 2023

SeedAL and H3WB got accepted to the IEEE International Conference on Computer Vision (ICCV) 2023!

May 2023

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 arXiv. Code is available at here.

Dec 2022

Our paper entitled “H3WB: Human3.6M 3D WholeBody Dataset and Benchmark” is now available on arXiv. H3WB Dataset and benchmark are available here.

Oct 2022

Our paper entitled “A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation” is accepted to the IEEE Winter Conference on Applications of Computer Vision (WACV).

Aug 2022

Our extended work on HoughNet is accepted to the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).

Nov 2021

I am among the outstanding BMVC2021 reviewers!

Nov 2021

I started my Postdoc at École des Ponts (ENPC) ParisTech, IMAGINE Research Group.

Oct 2021

I will be co-organizing the Women in Computer Vision Workshop at CVPR 2022.

Sep 2021

I successfully defended my Ph.D thesis. Here is my acedemic family tree (source).

Sep 2021

HPRNet is accepted to Image and Vision Computing: publisher's page

Jun 2021

Our paper entitled “HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation” is now available on arXiv.

May 2021

Our paper “Adversarial Segmentation Loss for Sketch Colorization” is accepted to the International Conference on Image Processing (ICIP).

Apr 2021

Our extended work on HoughNet, “HoughNet: Integrating near and long-range evidence for visual detection” is now available on arXiv.

Feb 2021

Our paper entitled “Adversarial Segmentation Loss for Sketch Colorization” is now available on arXiv.

Oct 2020

I will be co-organizing the Women in Computer Vision Workshop at CVPR 2021.

Sep 2020

Our work GANILLA has been featured in “The Batch”, a new weekly newsletter from deeplearning.ai.

Aug 2020

Our paper entitled “Reducing Label Noise in Anchor-Free Object Detection” is accepted to the British Machine Vision Conference (BMVC).

Jun 2020

Our paper entitled “HoughNet: Integrating near and long-range evidence for bottom-up object detection” is accepted to the European Conference on Computer Vision (ECCV).

Jan 2020

Our paper entitled “GANILLA: Generative adversarial networks for image to illustration translation” is accepted to Image and Vision Computing.


Research

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


Nermin Samet, Oriane Siméoni, Gilles Puy, Georgy Ponimatkin, Renaud Marlet, Vincent Lepetit
IEEE International Conference on Computer Vision (ICCV) 2023

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


Yue Zhu, Nermin Samet, David Picard
IEEE International Conference on Computer Vision (ICCV) 2023

A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation


Georgy Ponimatkin, Nermin Samet, Yang Xiao, Yuming Du, Renaud Marlet, Vincent Lepetit
IEEE Winter Conference on Applications of Computer Vision (WACV) 2022

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


Nermin Samet, Samet Hicsonmez, Emre Akbas
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2022

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


Nermin Samet, Emre Akbas
Image and Vision Computing (IMAVIS) 2021

Adversarial Segmentation Loss for Sketch Colorization


Samet Hicsonmez, Nermin Samet, Emre Akbas, Pinar Duygulu
International Conference on Image Processing (ICIP) 2021

Reducing Label Noise in Anchor-Free Object Detection


Nermin Samet, Samet Hicsonmez, Emre Akbas
British Machine Vision Conference (BMVC) 2020

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


Nermin Samet, Samet Hicsonmez, Emre Akbas
European Conference on Computer Vision (ECCV) 2020

GANILLA: Generative adversarial networks for image to illustration translation


Samet Hicsonmez, Nermin Samet, Emre Akbas, Pinar Duygulu
Image and Vision Computing (IMAVIS) 2020

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


Nermin Samet, Samet Hicsonmez, Pinar Duygulu, Emre Akbas
Signal Processing and Communications Applications Conference (SIU) 2017

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


Nermin Samet, Jochen Zeil, Elmar Mair, Norbert Boeddeker, Wolfgang Stuerzl
International Conference on Simulation of Adaptive Behavior (SAB) 2014, Best Paper Finalist

Inspired from Jon Barron's website