World's Best Scientists 2026 revealed!
Marius Leordeanu

Marius Leordeanu

D-Index & Metrics

Computer Science

D-Index
30
Citations
7641
World Ranking
13852
National Ranking
5

Overview

Marius Leordeanu is affiliated with the Romanian Academy in Romania and specializes primarily in Computer Science, with an extensive publication record in the subfields of Computer Vision and Pattern Recognition, Artificial Intelligence, Experimental and Cognitive Psychology, Cognitive Neuroscience, and Radiology, Nuclear Medicine and Imaging.

Their research covers several main topics including:

  • Advanced Image and Video Retrieval Techniques
  • Multimodal Machine Learning Applications
  • Video Surveillance and Tracking Methods
  • Visual Attention and Saliency Detection
  • Advanced Neural Network Applications
  • Domain Adaptation and Few-Shot Learning
  • Robotics and Sensor-Based Localization

Among recent papers, notable publications include:

  • "TeachText: CrossModal Generalized Distillation for Text-Video Retrieval," 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
  • "An Investigation of Various Machine and Deep Learning Techniques Applied in Automatic Fear Level Detection and Acrophobia Virtual Therapy," 2020, Sensors
  • "Integrating Biosignals Measurement in Virtual Reality Environments for Anxiety Detection," 2020, Sensors
  • "Anatomically aware dual-hop learning for pulmonary embolism detection in CT pulmonary angiograms," 2024, Computers in Biology and Medicine
  • "Driven by Vision: Learning Navigation by Visual Localization and Trajectory Prediction," 2021, Sensors

The scholar has frequently published in venues such as arXiv (Cornell University), Sensors, Journal of Financial Studies, Artificial Intelligence, and the 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

Frequent co-authors in their works include Dragoş Costea, Alin Moldoveanu, Gabriela Moise, Florica Moldoveanu, and Oana Bălan.

In addition to journal and conference publications, this researcher has contributed to book literature with a publication at Springer International Publishing titled Unsupervised Learning in Space and Time, published in 2020.

Best Publications

  • Online selection of discriminative tracking features

    R.T. Collins;Yanxi Liu;M. Leordeanu

  • A spectral technique for correspondence problems using pairwise constraints

    M. Leordeanu;M. Hebert

  • The Moving Pose: An Efficient 3D Kinematics Descriptor for Low-Latency Action Recognition and Detection

    Mihai Zanfir;Marius Leordeanu;Cristian Sminchisescu

  • An Integer Projected Fixed Point Method for Graph Matching and MAP Inference

    Marius Leordeanu;Martial Hebert;Rahul Sukthankar

  • Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation

    Julien Mairal;Marius Leordeanu;Francis Bach;Martial Hebert

  • Unsupervised Learning for Graph Matching

    Marius Leordeanu;Rahul Sukthankar;Martial Hebert

  • Automated feature-based range registration of urban scenes of large scale

    I. Stamos;M. Leordeanu

  • Discovering texture regularity as a higher-order correspondence problem

    James Hays;Marius Leordeanu;Alexei A. Efros;Yanxi Liu

  • Beyond Local Appearance: Category Recognition from Pairwise Interactions of Simple Features

    M. Leordeanu;M. Hebert;R. Sukthankar

  • How Hard Can It Be? Estimating the Difficulty of Visual Search in an Image

    Radu Tudor Ionescu;Bogdan Alexe;Marius Leordeanu;Marius Popescu

  • New methods for digital modeling of historic sites

    P.K. Allen;A. Troccoli;B. Smith;S. Murray

  • TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval

    Ioana Croitoru;Simion-Vlad Bogolin;Yang Liu;Samuel Albanie

  • 3D modeling of historic sites using range and image data

    P.K. Allen;I. Stamos;A. Troccoli;B. Smith

  • Shift R-CNN: Deep Monocular 3D Object Detection With Closed-Form Geometric Constraints

    Andretti Naiden;Vlad Paunescu;Gyeongmo Kim;ByeongMoon Jeon

  • Efficient closed-form solution to generalized boundary detection

    Marius Leordeanu;Rahul Sukthankar;Cristian Sminchisescu

  • Emotion Classification Based on Biophysical Signals and Machine Learning Techniques

    Oana Bălan;Gabriela Moise;Livia Petrescu;Alin Moldoveanu

  • Locally Affine Sparse-to-Dense Matching for Motion and Occlusion Estimation

    Marius Leordeanu;Andrei Zanfir;Cristian Sminchisescu

  • Aerial image geolocalization from recognition and matching of roads and intersections.

    Dragos Costea;Marius Leordeanu

  • Fear Level Classification Based on Emotional Dimensions and Machine Learning Techniques

    Oana Bălan;Gabriela Moise;Alin Moldoveanu;Marius Leordeanu

  • Semi-supervised learning and optimization for hypergraph matching

    Marius Leordeanu;Andrei Zanfir;Cristian Sminchisescu

  • Smoothing-based Optimization

    M. Leordeanu;M. Hebert

  • An Investigation of Various Machine and Deep Learning Techniques Applied in Automatic Fear Level Detection and Acrophobia Virtual Therapy.

    Oana Bălan;Gabriela Moise;Alin Moldoveanu;Marius Leordeanu

Frequent Co-Authors

Rahul Sukthankar
Rahul Sukthankar Google (United States)
Martial Hebert
Martial Hebert Carnegie Mellon University
Cristian Sminchisescu
Cristian Sminchisescu Google (United States)
Yanxi Liu
Yanxi Liu Pennsylvania State University
Vittorio Ferrari
Vittorio Ferrari Google (United States)
Alexei A. Efros
Alexei A. Efros University of California, Berkeley
Shumeet Baluja
Shumeet Baluja Google (United States)
James Hays
James Hays Georgia Institute of Technology
Peter K. Allen
Peter K. Allen Columbia University
Yang Liu
Yang Liu Tsinghua University

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring Computer Science in the USA opens up a wealth of flexible online study options for learners at all stages. Many are now looking beyond traditional paths to find programs that better suit their needs, schedules, or budgets.

For those considering further specialization, it’s helpful to review what masters program should I do to align your studies with in-demand career fields. If you need a faster entry or transition, 2 year online degrees can provide technical training and job skills in a shorter timeframe.

Cost is another key consideration. Researching the cheapest online degrees can help you find quality programs that won’t burden you with heavy debt. If your academic record isn’t perfect, don’t be discouraged—there are many options, including a college that accepts low gpa.

Each of these pathways can lead to rewarding technology careers or further academic opportunities, making it possible for more individuals to access the growing field of Computer Science.

Best Scientists Citing Marius Leordeanu

Trending Scientists