Multimedia Lab

Advancing Research in Artificial Intelligence, Information Retrieval and Data Science for Biomedical Imaging & Bioinformatics

Our lab pioneers advanced solutions in Artificial Intelligence, Information Retrieval and Data Science focusing on multimedia processing and fusion (signal, image, video, audio, text, sensor, synthetic) for diverse domains, including surveillance and security, media, medicine, fintech, and networking.

2nd Workshop on Artificial Intelligence for Multimedia
2nd Workshop on Artificial Intelligence for Multimedia
AI Multimedia Lab Team
AI Multimedia Lab Team
AI Multimedia Lab Team

Our Mission and Impact

At the Forefront of Artificial Intelligence, Information Retrieval, and Data Science for Multimedia

The AI Multimedia Lab (AIM), founded by Professor Bogdan IONESCU, is now part of the CAMPUS Research Institute, Politehnica Bucharest. With its roots dating back in 2007 with the creation of the Video Analysis and Processing Group within the Faculty of Electronics, Telecommunications and Information Technology, it evolved in the current format in 2016 with the creation of the CAMPUS Research Centre.

AIM is fostering advanced solutions in Artificial Intelligence, Information Retrieval and Data Science with a focus on multimedia information processing and fusion, e.g., signal, image, video, audio, text, sensor, synthetic, and algorithm benchmarking, for various use-cases and domains, e.g., surveillance & security, media, medicine, fintech, networking, to mention but a few.

AIM is also an educational hub entrusted within Politehnica Bucharest with the education, training and mentoring of students, graduates and early career engineers. It provides critical support across both academic and industrial initiatives, playing an essential role in facilitating R&D activities for the entire community.

  • +30 professors and researchers
  • +300 publications
  • +23 academia & industry projects
  • +12 company projects
  • +150 international collaborations
  • +150k CUDA cores and advanced infrastructure

Our Latest Events

Explore our recent conferences, workshops, and research initiatives that drive innovation in AI and multimedia technologies.

Expertise → Artificial IntelligenceExpertise → Signal ProcessingExpertise → Computer VisionExpertise → Text AnalysisExpertise → BiometricsExpertise → Biomedical ImagingExpertise → Artificial Intelligence → ensemble learningExpertise → Artificial Intelligence → classificationExpertise → Artificial Intelligence → clusteringExpertise → Artificial Intelligence → deep learningExpertise → Artificial Intelligence → embedded AIExpertise → Artificial Intelligence → generative modelsExpertise → Artificial Intelligence → graph modelsExpertise → Artificial Intelligence → knowledge representationExpertise → Artificial Intelligence → large scale learningExpertise → Artificial Intelligence → low-shot learningExpertise → Artificial Intelligence → multi-modal learningExpertise → Artificial Intelligence → large language modelsExpertise → Artificial Intelligence → neural networksExpertise → Artificial Intelligence → continual learningExpertise → Artificial Intelligence → quantum AIExpertise → Artificial Intelligence → temporal modelsExpertise → Artificial Intelligence → reinforcement learningExpertise → Signal Processing → audio processingExpertise → Signal Processing → super-resolutionExpertise → Signal Processing → computational photographyExpertise → Signal Processing → image retrievalExpertise → Signal Processing → cross-modal retrievalExpertise → Signal Processing → deepfake generationExpertise → Signal Processing → deepfake detectionExpertise → Signal Processing → image & video processingExpertise → Signal Processing → image speech forensicsExpertise → Signal Processing → speech recognitionExpertise → Signal Processing → speaker recognitionExpertise → Signal Processing → video summarizationExpertise → Signal Processing → visual question answeringExpertise → Computer Vision → action recognitionExpertise → Computer Vision → deformable modelsExpertise → Computer Vision → video analysisExpertise → Computer Vision → object detectionExpertise → Computer Vision → object recognitionExpertise → Computer Vision → multi-object trackingExpertise → Computer Vision → autonomous navigationExpertise → Computer Vision → scene understandingExpertise → Computer Vision → stereo and 3D visionExpertise → Computer Vision → vision and languageExpertise → Computer Vision → visual QAExpertise → Text Analysis → document AIExpertise → Text Analysis → document understandingExpertise → Text Analysis → DocVQAExpertise → Text Analysis → text recognitionExpertise → Text Analysis → Information extractionExpertise → Text Analysis → large models for OCRExpertise → Text Analysis → language processingExpertise → Text Analysis → scene text understandingExpertise → Text Analysis → writer identificationExpertise → Biometrics → affective computingExpertise → Biometrics → deepfakesExpertise → Biometrics → ethical & social issuesExpertise → Biometrics → face, speech biometricsExpertise → Biometrics → gait, soft biometricsExpertise → Biometrics → person re-identificationExpertise → Biometrics → privacyExpertise → Biometrics → bias & fairnessExpertise → Biomedical Imaging → image reconstructionExpertise → Biomedical Imaging → biostatisticsExpertise → Biomedical Imaging → clinical modelingExpertise → Biomedical Imaging → computer aided diagnosticsExpertise → Biomedical Imaging → medical applicationsExpertise → Biomedical Imaging → medical image analysisExpertise → Biomedical Imaging → neuroimagingArtificial IntelligenceSignal ProcessingComputer VisionText AnalysisBiometricsBiomedical Imagingensemble learningclassificationclusteringdeep learningembedded AIgenerative modelsgraph modelsknowledge representationlarge scale learninglow-shot learningmulti-modal learninglarge language modelsneural networkscontinual learningquantum AItemporal modelsreinforcement learningaudio processingsuper-resolutioncomputational photographyimage retrievalcross-modal retrievaldeepfake generationdeepfake detectionimage & video processingimage speech forensicsspeech recognitionspeaker recognitionvideo summarizationvisual question answeringaction recognitiondeformable modelsvideo analysisobject detectionobject recognitionmulti-object trackingautonomous navigationscene understandingstereo and 3D visionvision and languagevisual QAdocument AIdocument understandingDocVQAtext recognitionInformation extractionlarge models for OCRlanguage processingscene text understandingwriter identificationaffective computingdeepfakesethical & social issuesface, speech biometricsgait, soft biometricsperson re-identificationprivacybias & fairnessimage reconstructionbiostatisticsclinical modelingcomputer aided diagnosticsmedical applicationsmedical image analysisneuroimaging← Back

Our Research Domains

Explore our taxonomy of topics based on ACM & IEEE classification from existing publications

1

Artificial Intelligence

Machine learning, neural networks, and intelligent systems

2

Signal Processing

Digital signal analysis and processing techniques

3

Computer Vision

Image analysis and visual recognition systems

4

Biometrics

Identity verification through biological measurements

5

Biomedical Imaging

Medical image analysis and diagnostic imaging

6

Text Analysis

Natural language processing and text mining

Our Latest Projects

Explore our portfolio of academic research and industry collaborations

AI4MEDIABENCH

Benchmarking AI models with Fairness, Reproducibility, and Impact

AI4MediaBench, developed by UPB’s AI Multimedia Lab, is an online Evaluation-as-a-Service platform that supports the creation, maintenance, and management of benchmarking competitions. It enables AI researchers and developers to evaluate and share tools systematically, ensuring ethical principles such as data protection, fairness, robustness, and reproducibility.

Organizers can design benchmarks for internal decision-making or public challenges, selecting optimal AI models for deployment. The platform offers standardized datasets, metrics, and evaluation scripts, automatic error detection, containerized execution, API integration, and support for distributed computing. It can also include computational efficiency metrics, encouraging environmentally responsible AI.

+1500

Researchers

+1000

Submissions

+50

Benchmarks

1

Define the Challenge

Specify the problem, evaluation metrics, and submission type to create a clear and fair benchmark.

2

Prepare and Run

Upload datasets, configure tasks, and launch the benchmark with reproducible execution environments.

3

Evaluate and Share

Run submissions, generate leaderboards, and make results openly accessible to the community.

Meet the Team

Get to know the drive and vibe behind our results

Our team combines academic and R&D contributors with close industry and international collaborators. We are also proud of our alumni who are now leaders in their own domain.

See All Members
Oriana PRESACAN

Oriana PRESACAN

PhD Student

Adriana-Victorița MIU

Adriana-Victorița MIU

PhD Student

Maria ONIGA

Maria ONIGA

PhD Student

Bogdan IONESCU

Prof. Bogdan IONESCU

Leader

PhD supervisor

Dr. Ruxandra ȚAPU

Dr. Ruxandra ȚAPU

Professor

PhD supervisor

Dr. Bogdan MOCANU

Dr. Bogdan MOCANU

Assoc.Prof.

PhD supervisor

Dr. Dragoș ȚARĂLUNGĂ

Dr. Dragoș ȚARĂLUNGĂ

Assoc.Prof.

PhD supervisor

Dr. Alina SULTANA

Dr. Alina SULTANA

Assoc.Prof.

PhD supervisor

Dr. Mihai-Gabriel CONSTANTIN

Dr. Mihai-Gabriel CONSTANTIN

Lecturer

Dr. Liviu-Daniel ȘTEFAN

Dr. Liviu-Daniel ȘTEFAN

Lecturer

Dr. Mihai DOGARIU

Dr. Mihai DOGARIU

Lecturer

Dr. Alina-Elena MARCU

Dr. Alina-Elena MARCU

Lecturer

Cristian STANCIU

Cristian STANCIU

JR/PhD Student

Alexandra ANDREI

Alexandra ANDREI

JR/PhD Student

Alexandru IONIȚĂ

Alexandru IONIȚĂ

JR/PhD Student

Alexe CIUREA

Alexe CIUREA

JR/PhD Student

Alexandru CIOBANU

Alexandru CIOBANU

JR/PhD Student

Ioan COMAN

Ioan COMAN

PhD Student

Valentina RIZEA

Valentina RIZEA

PhD Student

Lucian GRUIA

Lucian GRUIA

PhD Student

Octavian RADU

Octavian RADU

PhD Student

Andrei VIZUREANU

Andrei VIZUREANU

PhD Student

Irina-Ana VLAD

Irina-Ana VLAD

PhD Student

Adrian LUCA

Adrian LUCA

PhD Student

Ionuț Silviu SIMA

Ionuț Silviu SIMA

PhD Student

Adrian DINA

Adrian DINA

PhD Student

Oriana PRESACAN

Oriana PRESACAN

PhD Student

Adriana-Victorița MIU

Adriana-Victorița MIU

PhD Student

Maria ONIGA

Maria ONIGA

PhD Student

Bogdan IONESCU

Prof. Bogdan IONESCU

Leader

PhD supervisor

Dr. Ruxandra ȚAPU

Dr. Ruxandra ȚAPU

Professor

PhD supervisor

Dr. Bogdan MOCANU

Dr. Bogdan MOCANU

Assoc.Prof.

PhD supervisor

Trusted by leading academic, industry, and institutional partners worldwide.

+ 35

National & EU Research Projects

+ 150

Academic & Industry Collaborations

+ 50

Researchers, PhD Students & Contributors