no code implementations • 12 Feb 2024 • Alexandru-Raul Todoran, Marius Leordeanu
There is an increasing number of real-world problems in computer vision and machine learning requiring to take into consideration multiple interpretation layers (modalities or views) of the world and learn how they relate to each other.
no code implementations • 9 Feb 2024 • Dragos Costea, Alina Marcu, Cristina Lazar, Marius Leordeanu
Our goal is to track and analyze facial expressions, and other non-verbal cues in real-time, and use this information to build models that can predict and understand human behavior.
no code implementations • 29 Aug 2023 • Mihai Masala, Nicolae Cudlenco, Traian Rebedea, Marius Leordeanu
Artificial Intelligence makes great advances today and starts to bridge the gap between vision and language.
1 code implementation • 21 Aug 2023 • Mihai Pirvu, Alina Marcu, Alexandra Dobrescu, Nabil Belbachir, Marius Leordeanu
There are many ways of interpreting the world and they are highly interdependent.
no code implementations • 15 Aug 2023 • Alina Marcu, Mihai Pirvu, Dragos Costea, Emanuela Haller, Emil Slusanschi, Ahmed Nabil Belbachir, Rahul Sukthankar, Marius Leordeanu
Thus, each node could be an input node in some hyperedges and an output node in others.
no code implementations • 9 Aug 2023 • Lucian Bicsi, Bogdan Alexe, Radu Tudor Ionescu, Marius Leordeanu
We propose JEDI, a multi-dataset semi-supervised learning method, which efficiently combines knowledge from multiple experts, learned on different datasets, to train and improve the performance of individual, per dataset, student models.
no code implementations • 26 Jun 2023 • Alexandra Budisteanu, Dragos Costea, Alina Marcu, Marius Leordeanu
First, we manage to stay anchored in the real 3D world, by introducing an efficient multi-scale voxel carving method, which is able to accommodate significant noises in pose, depth, and illumination variations, while being able to reconstruct the view of the world from drastically different poses at test time.
no code implementations • 22 May 2023 • Mihai Masala, Nicolae Cudlenco, Traian Rebedea, Marius Leordeanu
GEST alows us to measure the similarity between texts and videos in a semantic and fully explainable way, through graph matching.
no code implementations • 30 Mar 2023 • Florin Condrea, Saikiran Rapaka, Lucian Itu, Puneet Sharma, Jonathan Sperl, A Mohamed Ali, Marius Leordeanu
Pulmonary Embolisms (PE) represent a leading cause of cardiovascular death.
no code implementations • 15 Dec 2022 • Elena Burceanu, Marius Leordeanu
Our motivation for a spectral space-time clustering approach, unique in video semantic segmentation literature, is that such clustering is dedicated to preserving object consistency over time, which we evaluate using our novel segmentation consistency measure.
1 code implementation • ICCV 2021 • Ioana Croitoru, Simion-Vlad Bogolin, Marius Leordeanu, Hailin Jin, Andrew Zisserman, Samuel Albanie, Yang Liu
In recent years, considerable progress on the task of text-video retrieval has been achieved by leveraging large-scale pretraining on visual and audio datasets to construct powerful video encoders.
1 code implementation • 26 Mar 2021 • Emanuela Haller, Elena Burceanu, Marius Leordeanu
The human ability to synchronize the feedback from all their senses inspired recent works in multi-task and multi-modal learning.
no code implementations • 13 Dec 2020 • Emanuela Haller, Adina Magda Florea, Marius Leordeanu
A novel spectral space-time clustering process on the graph produces unsupervised segmentation masks passed to the network as pseudo-labels.
no code implementations • COLING 2020 • Simion-Vlad Bogolin, Ioana Croitoru, Marius Leordeanu
Automatically describing videos in natural language is an ambitious problem, which could bridge our understanding of vision and language.
2 code implementations • 2 Oct 2020 • Alina Marcu, Vlad Licaret, Dragos Costea, Marius Leordeanu
Motivated by the lack of a large video aerial dataset, we also introduce Ruralscapes, a new dataset with high resolution (4K) images and manually-annotated dense labels every 50 frames - the largest of its kind, to the best of our knowledge.
3 code implementations • 2 Oct 2020 • Marius Leordeanu, Mihai Pirvu, Dragos Costea, Alina Marcu, Emil Slusanschi, Rahul Sukthankar
The unsupervised learning process is repeated over several generations, in which each edge becomes a "student" and also part of different ensemble "teachers" for training other students.
1 code implementation • NeurIPS 2021 • Iulia Duta, Andrei Nicolicioiu, Marius Leordeanu
Graph Neural Networks are perfectly suited to capture latent interactions between various entities in the spatio-temporal domain (e. g. videos).
no code implementations • 27 Jul 2020 • Marian Petrica, Radu D. Stochitoiu, Marius Leordeanu, Ionel Popescu
The second issue is that there were many factors which affected the evolution of the pandemic.
no code implementations • 23 Jun 2020 • Radu D. Stochiţoiu, Marian Petrica, Traian Rebedea, Ionel Popescu, Marius Leordeanu
More specifically, we want to statistically estimate all the relevant parameters for the new coronavirus COVID-19, such as the reproduction number, fatality rate or length of infectiousness period, based on Romanian patients, as well as be able to predict future outcomes.
no code implementations • 16 Apr 2020 • Florin Condrea, Victor-Andrei Ivan, Marius Leordeanu
Moreover, our system, which is trained in a purely automatic manner and needs no human annotation, also learns to predict the respiration or heart intensity signal for each moment in time and to detect the region of interest that is most relevant for the given task, e. g. the nose area in the case of respiration.
no code implementations • 22 Oct 2019 • Alina Marcu, Dragos Costea, Vlad Licaret, Marius Leordeanu
Semantic segmentation is a crucial task for robot navigation and safety.
1 code implementation • 20 Oct 2019 • Petru Soviany, Claudiu Ardei, Radu Tudor Ionescu, Marius Leordeanu
All strategies are first based on ranking the training images by their difficulty scores, which are estimated by a state-of-the-art image difficulty predictor.
Ranked #108 on Image Generation on CIFAR-10
no code implementations • 7 Oct 2019 • Iulia Paraicu, Marius Leordeanu
Our system learns to predict in real-time vehicle's current location and future trajectory, as a function of time, on a known map, given only the raw video stream and the intended destination.
no code implementations • 7 Jul 2019 • Emanuela Haller, Adina Magda Florea, Marius Leordeanu
While the actual matrix is not computed explicitly, the proposed algorithm efficiently computes, in a few iteration steps, the principal eigenvector that captures the segmentation of the main object in the video.
1 code implementation • 5 Jul 2019 • Elena Burceanu, Marius Leordeanu
Our method is based on the power iteration for finding the principal eigenvector of a matrix, which we prove is equivalent to performing a specific set of 3D convolutions in the space-time feature volume.
Ranked #45 on Semi-Supervised Video Object Segmentation on DAVIS 2016 (Jaccard (Mean) metric)
no code implementations • 23 May 2019 • Andretti Naiden, Vlad Paunescu, Gyeongmo Kim, ByeongMoon Jeon, Marius Leordeanu
We propose Shift R-CNN, a hybrid model for monocular 3D object detection, which combines deep learning with the power of geometry.
1 code implementation • NeurIPS 2019 • Andrei Nicolicioiu, Iulia Duta, Marius Leordeanu
Our model is general and could learn to recognize a variety of high level spatio-temporal concepts and be applied to different learning tasks.
Ranked #58 on Action Recognition on Something-Something V1 (using extra training data)
no code implementations • 14 Aug 2018 • Ioana Croitoru, Simion-Vlad Bogolin, Marius Leordeanu
We train a student deep network to predict the output of a teacher pathway that performs unsupervised object discovery in videos or large image collections.
no code implementations • 5 Jun 2018 • Iulia Duta, Andrei Liviu Nicolicioiu, Simion-Vlad Bogolin, Marius Leordeanu
Here we propose an approach to describe videos in natural language by reaching a consensus among multiple encoder-decoder networks.
no code implementations • 5 Apr 2018 • Elena Burceanu, Marius Leordeanu
We address this challenge by proposing a deep neural network composed of different parts, which functions as a society of tracking parts.
no code implementations • 4 Apr 2018 • Alina Marcu, Dragos Costea, Emil Slusanschi, Marius Leordeanu
The first stage of our network predicts pixelwise class labels, while the second stage provides a precise location using two branches.
no code implementations • 26 May 2017 • Elena Burceanu, Marius Leordeanu
They are classifiers that respond at different scales and locations.
no code implementations • CVPR 2016 • Radu Tudor Ionescu, Bogdan Alexe, Marius Leordeanu, Marius Popescu, Dim P. Papadopoulos, Vittorio Ferrari
We address the problem of estimating image difficulty defined as the human response time for solving a visual search task.
no code implementations • ICCV 2017 • Emanuela Haller, Marius Leordeanu
We also present theoretical properties of our unsupervised learning method, that under some mild constraints is guaranteed to learn a correct discriminative classifier even in the unsupervised case.
no code implementations • ICCV 2017 • Ioana Croitoru, Simion-Vlad Bogolin, Marius Leordeanu
Our approach is different from the published literature that performs unsupervised discovery in videos or in collections of images at test time.
no code implementations • 26 May 2016 • Dragos Costea, Marius Leordeanu
We offer a complete pipeline for geolocalization, from the detection of roads and intersections, to the identification of the enclosing geographic region by matching detected intersections to previously learned manually labeled ones, followed by accurate geometric alignment between the detected roads and the manually labeled maps.
no code implementations • 18 May 2016 • Alina Marcu, Marius Leordeanu
Our model learns to combine local object appearance as well as information from the larger scene at the same time and in a complementary way, such that together they form a powerful classifier.
no code implementations • 1 Dec 2015 • Marius Leordeanu, Alexandra Radu, Shumeet Baluja, Rahul Sukthankar
Our method works both as a feature selection mechanism and as a fully competitive classifier.
no code implementations • 20 Nov 2015 • Anirudh Goyal, Marius Leordeanu
Integrating higher level visual and linguistic interpretations is at the heart of human intelligence.
no code implementations • 27 Nov 2014 • Marius Leordeanu, Alexandra Radu, Rahul Sukthankar
Feature selection is an essential problem in computer vision, important for category learning and recognition.
no code implementations • 2 Apr 2014 • Marius Leordeanu, Rahul Sukthankar
In this manner we can learn and grow both a deep, complex graph of classifiers and a rich pool of features at different levels of abstraction and interpretation.
no code implementations • NeurIPS 2009 • Marius Leordeanu, Martial Hebert, Rahul Sukthankar
When applied to MAP inference, the algorithm is a parallel extension of Iterated Conditional Modes (ICM) with climbing and convergence properties that make it a compelling alternative to the sequential ICM.