Hi 🌸! I am Lili and I am a postdoctoral researcher under the supervision of Prof. Dr. Zeynep Akata. I obtained by Ph.D in Computer Vision from the University of Bucharest under the supervision of Prof. Dr. Radu Ionescu. I previously worked on video anomaly detection and medical image analysis. My current research interests are self-supervision and multi-modal learning.

My goal is to conduct impactful deep learning research, while cultivating empathy and promoting growth and collaboration.

A short summary about my academic achivements:

Iuliana Georgescu is a Computer Vision Researcher with a PhD in Computer Vision from the University of Bucharest. Currently a Postdoctoral Researcher at Helmholtz Munich, she specializes in multimodal learning, video anomaly detection, and medical image analysis. She has interned at Google and Amazon, contributed to top-tier conferences (CVPR, ICCV, ECCV), and received multiple awards, including the Best Romanian AI PhD Thesis Award (2024). She has co-authored several high-impact publications and serves as a reviewer for major ML/CV conferences and journals. She actively collaborates with industry and academia to advance deep learning research.

Education

• Feb 2024 - Now - Postdoc, Helmholtz Munich, Germany.
• Oct 2019 - Sep 2023 - PhD in Computer Science, Faculty of Mathematics and Computer Science, University of Bucharest, Romania.
• Oct 2017 - Jun 2019 - MsC in Artificial Intelligence, Faculty of Mathematics and Computer Science, University of Bucharest, Romania.
• Oct 2014 - Jun 2017 - BsC in Computer Science, Faculty of Mathematics and Computer Science, University of Bucharest, Romania.

Internships

• Aug 2022 - Nov 2022 - Research Intern, Google, France.
• Nov 2020 - Feb 2021 - Applied Scientist Intern, Amazon, Germany.

Awards

• Awared the Best Romanian AI PhD Thesis organized by RAID 2024, Romania 2024
• Awarded the third prize in the „Young Researchers in Science and Engineering Contest 2023” organized by the Cluj-Napoca City Hall, Romania.
• Participant of the CVPR Doctoral Consortium 2023 (13% acceptance rate), Canada.
• Awarded the first prize in the „Student Scientific Communications Session 2022” organized by the Faculty of Mathematics and Computer Science, University of Bucharest, Romania.

Selected Publications

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training

Sanghwan Kim, Rui Xiao, Mariana-Iuliana Georgescu, Stephan Alaniz, Zeynep Akata
CVPR, 2025
[Paper]

..

FLAIR: VLM with Fine-grained Language-informed Image Representations

Rui Xiao, Sanghwan Kim, Mariana-Iuliana Georgescu, Zeynep Akata, Stephan Alaniz
CVPR, 2025
[Paper]

..

EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval

Thomas Hummel, Shyamgopal Karthik, Mariana-Iuliana Georgescu, Zeynep Akata
ECCV, 2024
[Paper]

..

Audiovisual Masked Autoencoders

Mariana-Iuliana Georgescu*, Eduardo Fonseca, Radu Tudor Ionescu, Mario Lucic, Cordelia Schmid, Anurag Arnab*, *equal contribution
ICCV, 2023
[Paper]

..

Multimodal Multi-Head Convolutional Attention with Various Kernel Sizes for Medical Image Super-Resolution

Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Andreea-Iuliana Miron, Olivian Savencu, Nicolae-Catalin Ristea, Nicolae Verga, Fahad Shahbaz Khan
WACV, 2023
[Paper] [Code]

..

UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection

Andra Acsintoae*, Andrei Florescu*, Mariana-Iuliana Georgescu*, Tudor Mare*, Paul Sumedrea*, Radu Tudor Ionescu, Fahad Shahbaz Khan, Mubarak Shah, *equal contribution
CVPR, 2022
[Paper] [Code]

..

A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video

Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Fahad Shahbaz Khan, Marius Popescu and Mubarak Shah
TPAMI, 2022
[Paper] [Code]

..

Anomaly Detection in Video via Self-Supervised and Multi-Task Learning

Mariana-Iuliana Georgescu, Antonio Barbalau, Radu Tudor Ionescu, Fahad Shahbaz Khan, Marius Popescu, Mubarak Shah
CVPR, 2021
[Paper] [Code]

..