Dan Oneață

Picture of Dan Oneata

Hello and welcome to my web-page! My name is Dan and I'm a research scientist at the Politehnica University of Bucharest in the SpeeD lab. Previously, I have worked at Eloquentix tackling data science tasks. I have received my PhD in computer vision and machine learning from the Université Grenoble Alpes, where I was fortunate to work under the supervision of Dr. Cordelia Schmid and Dr. Jakob Verbeek. My research interests include general machine learning techniques and its applications to computer vision, speech, and natural language processing. Currently I'm fascinated by category theory and its applications.


Below is a selection of my publications. You can find the complete list on my Google scholar profile.

Optical flow stabilization
Journal paper
A Robust and Efficient Video Representation for Action Recognition
International Journal of Computer Vision, Springer Verlag, 2015, pp.1-20.
Heng Wang, Dan Oneață, Jakob Verbeek and Cordelia Schmid.
paper · code
Spatio temporal proposals
Conference paper
Spatio-Temporal Object Detection Proposals
European Conference on Computer Vision, 2014.
Dan Oneață, Jérôme Revaud, Jakob Verbeek and Cordelia Schmid.
paper · poster · code
Approximate normalization of Fisher vectors
Conference paper
Efficient Action Localization with Approximately Normalized Fisher Vectors
IEEE Conference on Computer Vision and Pattern Recognition, 2014.
Dan Oneață, Jakob Verbeek and Cordelia Schmid.
paper · poster
Action recognition results
Conference paper
Action and Event Recognition with Fisher Vectors on a Compact Feature Set
IEEE International Conference on Computer Vision, 2013.
Dan Oneață, Jakob Verbeek and Cordelia Schmid.
paper · poster · code


University of Grenoble logo
Doctoral thesis
Robust and Efficient Models for Action Recognition and Localization
Université Grenoble Alpes, 2015.
Dan Oneață
thesis · slides
University of Edinburgh logo
Master's thesis
Fast Low-Rank Metric Learning
University of Edinburgh, 2011.
Dan Oneață
thesis · slides
Politehnica University of Bucharest logo
Bachelor's thesis (in Romanian)
Detecția de fețe utilizând metoda Viola-Jones
"Politechnica" University of Bucharest, 2010.
Dan Oneață
thesis · slides


Bucharest CV logo
Paper presentation
Deep Image Prior
Bucharest CV reading group · Bucharest, Romania · February, 2018
Bucharest FP logo
Coding dojo
A simple Sudoku solver in Haskell
Bucharest FP meet-up · Bucharest, Romania · June, 2017
SpeeD lab logo
Short course
An Introduction to Machine Learning
Course at SpeeD lab · Bucharest, Romania · June, 2016
lecture 1 · lecture 2 · lecture 3 · lecture 4
Eloquentix logo
An Introduction to Machine Learning
Eloquentix annual meeting · Brașov, Romania · October, 2015
Meet up logo
A Tutorial on Action Recognition in Video
Grenoble Data Science meet-up · Grenoble, France · March, 2015
Keynote format
Thumos'14 logo
LEAR–INRIA Submission at Thumos’14
THUMOS'14 workshop · Zürich, Switzerland · September, 2014
classification · detection
slides for the two challenges
NIST logo
TRECVid'13 workshop · Gaithersburg, USA · November, 2013
Graphical models
Paper presentation
A Thousand Frames in Just a Few Words
LEAR–XRCE reading group · Grenoble, France · August, 2013
Spectral learning
Paper presentation
A Spectral Algorithm for Learning Hidden Markov Models
LEAR–XRCE reading group · Grenoble, France · March, 2013
slides · resources
Stochastic gradient with Langevin dynamics
Paper presentation
Posterior Sampling with Stochastic Gradients
LEAR reading group · Grenoble, France · July, 2012
Latent temporal model
Paper presentation
Learning Latent Temporal Structure for Complex Event Detection
LEAR reading group · Grenoble, France · August, 2012


Scratchpad · link
being a collection of notes.
Code gist
Fisher vectors · link
being a minimal Python implementation of the Fisher vectors method based on numpy and scikit-learn. For an application of Fisher vectors for action recognition in videos, check out the fv4a repository.
Code gist
Sudoku · link
being an exploration into applicative functors and a solution to a puzzle by Conor McBride. The snippet was highlighted as an example of functor-oriented programming. For more exercises on the functorial kit checkout this other exercise from Conor McBride and Jeremy Gibbons's paper, Calculating Functional Programs.
Diacritics restoration · link
being a machine learning challenge I set up for the second-year students. The goal was to add the missing diacritics marks for a given text in Romanian.
Haskell playground · link
being the place where I indulge myself with Haskell. You'll find the usual goodies: free monoids, comondas, anamorphisms and others.
Algebra of programming · link
being an incomplete cheatsheet of equational properties in category theory to ease my way through the Algebra of Programming book.