BrainMap

Andrei Racoviteanu

- UNIVERSITATEA NAŢIONALĂ DE ŞTIINŢĂ ŞI TEHNOLOGIE POLITEHNICA BUCUREŞTI

Researcher | Teaching staff

Expertise & keywords

Transfer Learning for Image Aesthetic Assessment Call name: P 1 - SP 1.1 - Proiecte de cercetare pentru stimularea tinerelor echipe independente
PN-III-P1-1.1-TE-2019-0543 2020 - 2022

Role in this project:

Coordinating institution: UNIVERSITATEA POLITEHNICA DIN BUCURESTI

Project partners: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO)

Affiliation: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO)

Project website: http://imag.pub.ro/translate/

Abstract:

The project aims to develop transfer learning methods for deep convolutional networks. In this framework, besides the main database, which allows supervised learning, we will consider a second database, larger in volume, that contains examples either without annotations or with labels, but for another, related, problem. The transfer learning involves extracting useful information from the second database to increase performance on the primary set, in a simultaneous process.

For the development of the transfer learning algorithm, the characteristics of the convolutional networks to form descriptors on the intermediate layers, respectively to be sequentially trained are exploited. The central algorithmic principle is the partitioning by clustering (if the data does not have labels) or by classifying the secondary data set, where the descriptors of data are extracted on an intermediate layer. The network is required to create descriptors that provide wide margins between the data of one group and the centroid of another group. The groups can be associated with the classes from the primary database and the method of calculating the wide margin will be explored. Secondly, for the harmonization of the two databases we will use regularization by injecting a random perturbation, in an annealed process, into the global gradient.

From an application point of view, we aim to estimate the aesthetic value of a photograph. The aesthetic value aggregates, consciously or unconsciously, how pleasing an image looks. For high performance, in this direction we will exploit the previously developed transfer learning algorithm. The application is useful in commercial area to offer customers visual quality.

Technologies and innovative video systems for person re-identification and analysis of dissimulated behavior Call name: P 2 - SP 2.1 - SOLUTII - 2 - Tehnologii şi sisteme video/audio inovative
PN-III-P2-2.1-SOL-2016-02-0002 2017 - 2020

Role in this project:

Coordinating institution: UNIVERSITATEA POLITEHNICA DIN BUCURESTI

Project partners: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO); UTI GRUP S.A. (RO); Ministerul Apararii Nationale prin Agentia de Cercetare pentru Tehnica si Tehnologii Militare (ACTTM) (RO)

Affiliation: UNIVERSITATEA POLITEHNICA DIN BUCURESTI (RO)

Project website: http://campus.pub.ro/lab7/spiava/

Abstract:

Within the actual context of terrorist threats, SPIA-VA aims to develop intelligent systems for automatic person re-identification, detection of dissimulated behavior and speech analysis. The proposed system is inherently multi-modal via processing of multiple and variable quality sources, e.g., video, audio, text, infrared, depth, thermal, as well as the fusion of these. The proposed solution pushes forward the state of the art in deep learning and is designed to respond to a large variety of functional and operational scenarios. It is to be validated in real world scenarios, developed in cooperation with the beneficiary military public institutions.

FILE DESCRIPTION	DOCUMENT
List of research grants as project coordinator or partner team leader
Significant R&D projects for enterprises, as project manager
R&D activities in enterprises
Peer-review activity for international programs/projects