LOOSE Research Group

The LOOSE Research Group, led by Dr.Radu Marinescu, is focused on the evolution and re-engineering of object-oriented software systems.

LOOSE recognizes that an organization can evolve only through its members and that these members may have various ideals that must be integrated into the organization's objectives. All research activities of the LOOSE Research Group follow an iterative approach starting with basic research which is then concretized in two directions: on the one hand in the academic field, and on the other hand in collaborations with the industry.

06/10/2022

Best Paper Award - Facultatea de Automatică și Calculatoare - Timișoara Articolul intitulat “Towards the Detection of Hidden Familial Type Correlations in Java Code” a primit distincția “Best Paper Award” a […]

12/02/2020

BTC Embedded Systems Upgrades the DCTI Software Design Laboratory | Departamentul Calculatoare şi Tehnologia Informaţiei BTC Embedded Systems and its subsidiary BTC Embedded Systems Romania completely reequipped the Software Design Laboratory (B528a) with 20 brand-new state-of-the-art computers (Intel i7 - 9700, 16 GB RAM, 256 GB SSD, 21.5’' Monitor).

22/08/2018

Nice real examples of what may happen if you do this ;)

The Dangers of Copy and Paste Copying and pasting code is the most common form of reused in software development despite the problems it creates. Advanced static analysis tools outperform simple tools that detect copy and pasted code by only real, often subtle, errors in the copied code.

03/10/2017

La inițiativa companiei Bitdefender și cu susținerea lor, dl. Marius Minea predă în acest semestru un curs facultativ, "Code: analysis, bugs, and security". Cursul se desfășoară miercuri de la 8 la 10 în ASPC, cu prima întâlnire introductivă în săptămâna 2 (4.10.2017). Cei interesați sunt rugați să se înscrie folosind formularul de mai jos:

https://docs.google.com/forms/d/1cuUbEIfh15wVefuKflMUqb-uTI0t-cVNdLOhMEaOYIA/

26/01/2017

Abstract: The automatic interpretation of video sequences at higher level of abstraction poses some of the biggest challenges in computer science today. It requires processing large amounts of visual data as fast as possible while being able to learn the meaningful information as accurately as possible. It uses the most advanced high performance computers available today and the most advanced machine learning algorithms. The spatiotemporal coherence present in video also gives the possibility to conceive methods that learn in an unsupervised manner – another one of the important, still unsolved problems in artificial intelligence. By putting together many interesting challenges, and bringing together several fields in science and engineering, the problem of automatic video understanding can lead to the creation of novel technologies and also shed more light on our understanding of how the mind works. The brain does, in large part, vision, and that is what we also do, in our computer vision group. I will present some of the tasks we address, challenges that we face and solutions which we have found together with my students at the Institute of Mathematics of the Romanian Academy and University Politehnica of Bucharest. I will talk about several aspects of automatic video understanding, ranging from unsupervised learning to automatic translation of video content into language.

Bio: I am an Associate Professor at the University Politehnica of Bucharest and senior researcher at the Institute of Mathematics of the Romanian Academy. I am interested in the nature of intelligence, life and consciousness. In particular, my research focuses on computer vision, machine learning and robotics. At the university I teach the graduate level computer vision and robotics classes.
I have received a Ph.D. in Robotics from Carnegie Mellon University in 2009 and Bachelor degrees in Mathematics and Computer Science from the City University of New York, in 2003. My research has made contributions to learning and optimization for graph matching and probabilistic graphical models, object recognition and tracking, 3D modeling of urban scenes, boundary detection, optical flow, activity recognition, feature selection, object discovery and classification in video. In 2014 the Romanian Academy awarded me the “Grigore Moisil” Prize in Mathematics for my work on unsupervised learning for graph matching.

23/09/2016

La inițiativa companiei Bitdefender și cu susținerea lor, dl. Marius Minea predă în acest semestru un curs facultativ, "Code: analysis, bugs, and security". Cursul e miercuri de la 8 la 10 în ASPC, cu prima întâlnire introductivă din săptămâna 1.