Michal Koperski

Research Scientist

Tooploox

About me

I am a Research Scientist at Tooploox. I am working on projects which involve detection and recognition in images and videos. I am also a leader of a research project on incremental and multimodal learning.

I was a Post-doc at INRIA (STARS). My research focused on: action recognition, action detection, codebook representation, multimodal representation (RGB + Depth), spatio-temporal attention, deep learning.

My PhD thesis was supervised by Francois Bremond, the thesis was a part of Toyota Partner Robot project. In this project, we focused on assessing people’s cognitive and behavioral status, based on daily-living activities monitoring.

During my PhD I was a research intern at Disney Research Pittsburgh, I was working on codebook representations for People Re-Identification.

My CV can be found here.

Interests

Computer Vision
Action Recognition/Detection
Person Re-Identification
Machine Learning
Deep Learning

Education

PhD in Computing Science (Computer Vision), 2014-2017

INRIA, University of Nice Sophia-Antipolis
MSc in Computing Science, 2007-2009

Poznan University of Technology
BSc in Computing Science, 2004-2007

Poznan University of Technology

Details

From Aug 2018 I am a Research Scientist at Tooploox.

I am working on deep neural networks models for object recognition, detection on images and videos,
I am advising junior scientists,
I am working on a research project on incremental and multimodal learning (check our new publication),
I am working on code transfer to our industrial partners.

From Dec 2017 until Jul 2018 I was a Post-doc at INRIA (STARS).

I worked on deep neural networks with spatio-temporal attention for action recognition,
I worked on real-time action detection,
I worked on technology transfer to industrial partners
I published 6 scientific papers.

From Feb 2014 until Nov 2017 I was PhD Student at INRIA (STARS). During my PhD I:

I proposed, implemented and validated several methods for action recognition and action detection,
I published 9 scientific papers,
The code of the proposed methods was successfully transferred to Toyota.

From Jan 2016 until Apr 2016 I was a Research Intern at Disney Research Pittsburgh. I was working on codebook representation for People Re-Identification. During my internship:

I published 1 scientific paper,
1 patent request was filed.

From Apr 2013 until Sep 2013 I was Research Intern at INRIA (STARS). I was working on multimodal RGB-D representation for action recognition. During my internship I:

proposed, implemented and validated new RGB-D descriptor for action recognition,
I published 1 scientific paper.

From Apr 2010 until Apr 2012 I was Research Engineer at Poznan University of Technology (IDSS). I was working on automatic bird species detection, using machine learning. During the project I:

implemented and validated bird species detection system for mobile devices (ARM).
I published 1 book chapter

PhD

Download Abstract

On November 9th, 2017, I defended my Ph.D. thesis in Computer Science (Computer Vision) from the INRIA and from the University of Nice Sophia-Antipolis, France. The topic of my Ph.D. was “Human Action Recognition in Videos with Local Representation”. All the research involved in my thesis was conducted at INRIA under the supervision of Francois Bremond.

The jury of my Ph.D. defense was:

Frederic Precioso, Professor, University of Nice Sophia-Antipolis, president,
Matthieu Cord, Professor, Pierre and Marie Curie University, reviewer,
Leonid Sigal, Professor, University of British Columbia, reviewer,
Jean-Marc Odobez, Professor, IDIAP, examinator,
Francois Bremond, Research Director, INRIA (STARS), advisor.

Publications

More Publications

Plugin Networks for Inference under Partial Evidence
Michal Koperski, Tomasz Konopczynski, Rafal Nowak, Piotr Semberecki, Tomasz Trzcinski
In WACV (accepted for 2020), 2019.

PDF Bibtex

Toyota Smarthome: Real-World Activities of Daily Living
Srijan Das, Rui Dai, Michal Koperski, Luca Minciullo, Lorenzo Garattoni, Francois Bremond, Gianpiero Francesca
In ICCV, 2019.

PDF Project

A New Hybrid Architecture for Human Activity Recognition from RGB-D videos
Srijan Das, Monique Thonnat, Kaustubh Sakhalkar, Michal Koperski, Francois Bremond, Gianpiero Francesca
In MMM, 2019.

PDF Bibtex

Spatio-Temporal Grids for Daily Living Action Recognition
Srijan Das, Kaustubh Sakhalkar, Michal Koperski, Francois Bremond
In ICVGIP, 2018.

PDF Bibtex

Online temporal detection of daily-living human activities in long untrimmed video streams
Abhishek Goel, Abdelrahman Abubakr, Michal Koperski, Francois Bremond, Gianpiero Francesca
In IPAS, 2018.

PDF Bibtex

PRAXIS: Towards automatic cognitive assessment using gesture recognition
Farhood Negin, Pau Rodriguez, Michal Koperski, Adlen Kerboua, Jordi Gonzalez, Jeremy Bourgeois, Emmanuelle Chapoulie, Philippe Robert, Francois Bremond
In Expert Systems with Applications, 2018.

PDF Bibtex

Deep-Temporal LSTM for Daily Living Action Recognition
Srijan Das, Michal Koperski, Francois Bremond, Gianpiero Francesca
In AVSS, 2018.

PDF Bibtex

Action Recognition based on a mixture of RGB and Depth based skeleton
Srijan Das, Michal Koperski, Francois Bremond, Gianpiero Francesca
In AVSS, 2017.

PDF Bibtex

Groups Re-identification with Temporal Context
Michal Koperski, Slawomir Bak, Peter Carr
In ICMR, 2017.

PDF Bibtex

Online Recognition of Daily Activities by Color-Depth Sensing and Knowledge Models
Carlos Crispim-Junior, Alvaro Gomez Uria, Carola Strumia, Michal Koperski, Alexandra Konig, Farhood Negin, Serhan Cosar, Anh Tuan Nghiem, Duc Phu Chau, Guillaume Charpiat, Francois Bremond
In Sensors, 2017.

PDF Bibtex

Demos

Real Time Action Detection

The demo shows real-time action detection framework for daily-living patient monitoring.

Contact

m.koperski@gmail.com