no code implementations • EACL (VarDial) 2021 • Bharathi Raja Chakravarthi, Gaman Mihaela, Radu Tudor Ionescu, Heidi Jauhiainen, Tommi Jauhiainen, Krister Lindén, Nikola Ljubešić, Niko Partanen, Ruba Priyadharshini, Christoph Purschke, Eswari Rajagopal, Yves Scherrer, Marcos Zampieri
This paper describes the results of the shared tasks organized as part of the VarDial Evaluation Campaign 2021.
1 code implementation • VarDial (COLING) 2022 • Noëmi Aepli, Antonios Anastasopoulos, Adrian-Gabriel Chifu, William Domingues, Fahim Faisal, Mihaela Gaman, Radu Tudor Ionescu, Yves Scherrer
This report presents the results of the shared tasks organized as part of the VarDial Evaluation Campaign 2022.
no code implementations • VarDial (COLING) 2020 • Mihaela Gaman, Dirk Hovy, Radu Tudor Ionescu, Heidi Jauhiainen, Tommi Jauhiainen, Krister Lindén, Nikola Ljubešić, Niko Partanen, Christoph Purschke, Yves Scherrer, Marcos Zampieri
This paper presents the results of the VarDial Evaluation Campaign 2020 organized as part of the seventh workshop on Natural Language Processing (NLP) for Similar Languages, Varieties and Dialects (VarDial), co-located with COLING 2020.
1 code implementation • 20 Apr 2024 • Ana-Cristina Rogoz, Radu Tudor Ionescu
This work explores a novel data augmentation method based on Large Language Models (LLMs) for predicting item difficulty and response time of retired USMLE Multiple-Choice Questions (MCQs) in the BEA 2024 Shared Task.
no code implementations • 14 Apr 2024 • Diana-Nicoleta Grigore, Mariana-Iuliana Georgescu, Jon Alvarez Justo, Tor Johansen, Andreea Iuliana Ionescu, Radu Tudor Ionescu
Few-shot knowledge distillation recently emerged as a viable approach to harness the knowledge of large-scale pre-trained models, using limited data and computational resources.
1 code implementation • 15 Jan 2024 • Nicolae-Catalin Ristea, Andrei Anghel, Radu Tudor Ionescu
Subsequently, we combine language-specific Bidirectional Encoder Representations from Transformers (BERT) with Wav2Vec2. 0 audio features via a novel cascaded cross-modal transformer (CCMT).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
1 code implementation • 24 Oct 2023 • Jon Alvarez Justo, Joseph L. Garrett, Mariana-Iuliana Georgescu, Jesus Gonzalez-Llorente, Radu Tudor Ionescu, Tor Arne Johansen
Satellites are increasingly adopting on-board AI for enhanced autonomy through in-orbit inference.
1 code implementation • 10 Oct 2023 • Daria-Mihaela Broscoteanu, Radu Tudor Ionescu
Despite the importance of the task, to the best of our knowledge, there is no publicly available clickbait corpus for the Romanian language.
no code implementations • 29 Sep 2023 • Vlad Hondru, Radu Tudor Ionescu
Our empirical results on two data sets confirm the superiority of our framework over two state-of-the-art methods in the few-call model extraction scenario.
no code implementations • 26 Sep 2023 • Rafael-Edy Menadil, Mariana-Iuliana Georgescu, Radu Tudor Ionescu
Learning Using Privileged Information is a particular type of knowledge distillation where the teacher model benefits from an additional data representation during training, called privileged information, improving the student model, which does not see the extra representation.
1 code implementation • 6 Sep 2023 • Codrut Rotaru, Nicolae-Catalin Ristea, Radu Tudor Ionescu
We introduce RoDia, the first dataset for Romanian dialect identification from speech.
1 code implementation • 31 Aug 2023 • Neelu Madan, Nicolae-Catalin Ristea, Kamal Nasrollahi, Thomas B. Moeslund, Radu Tudor Ionescu
In this paper, we propose a curriculum learning approach that updates the masking strategy to continually increase the complexity of the self-supervised reconstruction task.
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 • 2 Aug 2023 • Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, Mubarak Shah
Our novel learning framework produces excellent results on the aforementioned task, yielding the highest gains when applied on the white-box model.
no code implementations • 27 Jul 2023 • Nicolae-Catalin Ristea, Radu Tudor Ionescu
We propose a novel cascaded cross-modal transformer (CCMT) that combines speech and text transcripts to detect customer requests and complaints in phone conversations.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
1 code implementation • 21 Jun 2023 • Nicolae-Catalin Ristea, Florinel-Alin Croitoru, Radu Tudor Ionescu, Marius Popescu, Fahad Shahbaz Khan, Mubarak Shah
We propose an efficient abnormal event detection model based on a lightweight masked auto-encoder (AE) applied at the video frame level.
Ranked #13 on
Anomaly Detection
on CUHK Avenue
no code implementations • 1 Jun 2023 • Alexandru Ghita, Radu Tudor Ionescu
The performance of neural networks in content-based image retrieval (CBIR) is highly influenced by the chosen loss (objective) function.
1 code implementation • 20 Feb 2023 • Eduard Poesina, Radu Tudor Ionescu, Josiane Mothe
To date, query performance prediction (QPP) in the context of content-based image retrieval remains a largely unexplored task, especially in the query-by-example scenario, where the query is an image.
1 code implementation • 15 Dec 2022 • Mihaela Gaman, Adrian-Gabriel Chifu, William Domingues, Radu Tudor Ionescu
We present a novel corpus for French dialect identification comprising 413, 522 French text samples collected from public news websites in Belgium, Canada, France and Switzerland.
2 code implementations • ICCV 2023 • Mariana-Iuliana Georgescu, Eduardo Fonseca, Radu Tudor Ionescu, Mario Lucic, Cordelia Schmid, Anurag Arnab
Can we leverage the audiovisual information already present in video to improve self-supervised representation learning?
Ranked #1 on
Audio Classification
on EPIC-KITCHENS-100
(using extra training data)
no code implementations • 28 Nov 2022 • Nicolae-Catalin Ristea, Florinel-Alin Croitoru, Dana Dascalescu, Radu Tudor Ionescu, Fahad Shahbaz Khan, Mubarak Shah
We propose a very fast frame-level model for anomaly detection in video, which learns to detect anomalies by distilling knowledge from multiple highly accurate object-level teacher models.
Ranked #16 on
Anomaly Detection
on CUHK Avenue
no code implementations • 22 Oct 2022 • Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Andreea-Iuliana Miron
In this work, we propose a novel strategy to generate ensembles of different architectures for medical image segmentation, by leveraging the diversity (decorrelation) of the models forming the ensemble.
1 code implementation • 25 Sep 2022 • Neelu Madan, Nicolae-Catalin Ristea, Radu Tudor Ionescu, Kamal Nasrollahi, Fahad Shahbaz Khan, Thomas B. Moeslund, Mubarak Shah
In this work, we extend our previous self-supervised predictive convolutional attentive block (SSPCAB) with a 3D masked convolutional layer, a transformer for channel-wise attention, as well as a novel self-supervised objective based on Huber loss.
Ranked #4 on
Anomaly Detection
on CUHK Avenue
1 code implementation • 10 Sep 2022 • Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, Mubarak Shah
Denoising diffusion models represent a recent emerging topic in computer vision, demonstrating remarkable results in the area of generative modeling.
no code implementations • 16 Jul 2022 • Antonio Barbalau, Radu Tudor Ionescu, Mariana-Iuliana Georgescu, Jacob Dueholm, Bharathkumar Ramachandra, Kamal Nasrollahi, Fahad Shahbaz Khan, Thomas B. Moeslund, Mubarak Shah
A self-supervised multi-task learning (SSMTL) framework for video anomaly detection was recently introduced in literature.
Ranked #2 on
Anomaly Detection
on CUHK Avenue
no code implementations • 7 Jul 2022 • Andrei Manolache, Florin Brad, Antonio Barbalau, Radu Tudor Ionescu, Marius Popescu
The DarkWeb represents a hotbed for illicit activity, where users communicate on different market forums in order to exchange goods and services.
no code implementations • 18 May 2022 • Florinel-Alin Croitoru, Nicolae-Catalin Ristea, Radu Tudor Ionescu, Nicu Sebe
In this work, we propose a novel curriculum learning approach termed Learning Rate Curriculum (LeRaC), which leverages the use of a different learning rate for each layer of a neural network to create a data-free curriculum during the initial training epochs.
Ranked #3 on
Speech Emotion Recognition
on CREMA-D
1 code implementation • 8 Apr 2022 • Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Andreea-Iuliana Miron, Olivian Savencu, Nicolae-Catalin Ristea, Nicolae Verga, Fahad Shahbaz Khan
Our attention module uses the convolution operation to perform joint spatial-channel attention on multiple concatenated input tensors, where the kernel (receptive field) size controls the reduction rate of the spatial attention, and the number of convolutional filters controls the reduction rate of the channel attention, respectively.
Ranked #1 on
Image Super-Resolution
on IXI
1 code implementation • 17 Mar 2022 • Nicolae-Catalin Ristea, Radu Tudor Ionescu, Fahad Shahbaz Khan
Following the successful application of vision transformers in multiple computer vision tasks, these models have drawn the attention of the signal processing community.
Ranked #1 on
Time Series Analysis
on Speech Commands
no code implementations • 14 Feb 2022 • Florinel-Alin Croitoru, Diana-Nicoleta Grigore, Radu Tudor Ionescu
During the training process, deep neural networks implicitly learn to represent the input data samples through a hierarchy of features, where the size of the hierarchy is determined by the number of layers.
no code implementations • 10 Feb 2022 • Adrian Sandru, Mariana-Iuliana Georgescu, Radu Tudor Ionescu
Recent studies revealed that convolutional neural networks do not generalize well to small image transformations, e. g. rotations by a few degrees or translations of a few pixels.
no code implementations • 28 Jan 2022 • Mihaela Gaman, Lida Ghadamiyan, Radu Tudor Ionescu, Marius Popescu
An important preliminary step of optical character recognition systems is the detection of text rows.
no code implementations • 20 Nov 2021 • Mariana-Iuliana Georgescu, Georgian Duta, Radu Tudor Ionescu
To this end, we study two knowledge distillation methods, one based on teacher-student training and one based on triplet loss.
4 code implementations • CVPR 2022 • Nicolae-Catalin Ristea, Neelu Madan, Radu Tudor Ionescu, Kamal Nasrollahi, Fahad Shahbaz Khan, Thomas B. Moeslund, Mubarak Shah
Our block is equipped with a loss that minimizes the reconstruction error with respect to the masked area in the receptive field.
Ranked #1 on
Anomaly Detection
on CUHK Avenue
(TBDC metric)
1 code implementation • CVPR 2022 • Andra Acsintoae, Andrei Florescu, Mariana-Iuliana Georgescu, Tudor Mare, Paul Sumedrea, Radu Tudor Ionescu, Fahad Shahbaz Khan, Mubarak Shah
This is a closed-set scenario that fails to test the capability of systems at detecting new anomaly types.
Ranked #5 on
Anomaly Detection
on CUHK Avenue
(using extra training data)
1 code implementation • 12 Oct 2021 • Nicolae-Catalin Ristea, Andreea-Iuliana Miron, Olivian Savencu, Mariana-Iuliana Georgescu, Nicolae Verga, Fahad Shahbaz Khan, Radu Tudor Ionescu
Our neural model can be trained on unpaired images, due to the integration of a multi-level cycle-consistency loss.
2 code implementations • 3 Sep 2021 • Tudor Mare, Georgian Duta, Mariana-Iuliana Georgescu, Adrian Sandru, Bogdan Alexe, Marius Popescu, Radu Tudor Ionescu
We propose a method for enhancing data sets containing faces without masks by creating synthetic masks and overlaying them on faces in the original images.
Ranked #1 on
Face Recognition
on CASIA-WebFace+masks
1 code implementation • 17 Aug 2021 • Ionut Cosmin Duta, Mariana Iuliana Georgescu, Radu Tudor Ionescu
On the one hand, we integrate CoConv in the widely-used residual networks and show improved recognition performance over baselines on the core tasks and benchmarks for visual recognition, namely image classification on the ImageNet data set and object detection on the MS COCO data set.
Ranked #121 on
Image Generation
on CIFAR-10
no code implementations • 22 Jul 2021 • Cezara Benegui, Radu Tudor Ionescu
Our change to the ABC protocol results in a multi-modal protocol that lowers the false acceptance rate for the attack proposed in our previous work to a percentage as low as 0. 07%.
1 code implementation • ACL 2021 • Ana-Cristina Rogoz, Mihaela Gaman, Radu Tudor Ionescu
In this work, we introduce a corpus for satire detection in Romanian news.
1 code implementation • 10 Apr 2021 • Radu Tudor Ionescu, Adrian Gabriel Chifu
We employ two classification methods as baselines for our new data set, one based on low-level features (character n-grams) and one based on high-level features (average of CamemBERT word embeddings).
no code implementations • EACL 2021 • Anca Tache, Gaman Mihaela, Radu Tudor Ionescu
Romanian is one of the understudied languages in computational linguistics, with few resources available for the development of natural language processing tools.
no code implementations • 22 Mar 2021 • Nicolae-Catalin Ristea, Radu Tudor Ionescu
Instead of just combining the models, we propose a self-paced ensemble learning scheme in which models learn from each other over several iterations.
Ranked #5 on
Speech Emotion Recognition
on CREMA-D
no code implementations • 20 Feb 2021 • Mihail Burduja, Radu Tudor Ionescu
To the best of our knowledge, we are the first to attempt to improve performance by training medical image registration models using curriculum learning, starting from an easy training setup in the first training stages, and gradually increasing the complexity of the setup.
no code implementations • EACL (VarDial) 2021 • Mihaela Gaman, Sebastian Cojocariu, Radu Tudor Ionescu
In this work, we describe our approach addressing the Social Media Variety Geolocation task featured in the 2021 VarDial Evaluation Campaign.
no code implementations • 25 Jan 2021 • Petru Soviany, Radu Tudor Ionescu, Paolo Rota, Nicu Sebe
Training machine learning models in a meaningful order, from the easy samples to the hard ones, using curriculum learning can provide performance improvements over the standard training approach based on random data shuffling, without any additional computational costs.
1 code implementation • 11 Jan 2021 • Anca Maria Tache, Mihaela Gaman, Radu Tudor Ionescu
Romanian is one of the understudied languages in computational linguistics, with few resources available for the development of natural language processing tools.
no code implementations • 21 Dec 2020 • Ismat Ara Reshma, Sylvain Cussat-Blanc, Radu Tudor Ionescu, Hervé Luga, Josiane Mothe
The class distribution of data is one of the factors that regulates the performance of machine learning models.
1 code implementation • CVPR 2021 • Mariana-Iuliana Georgescu, Antonio Barbalau, Radu Tudor Ionescu, Fahad Shahbaz Khan, Marius Popescu, Mubarak Shah
To the best of our knowledge, we are the first to approach anomalous event detection in video as a multi-task learning problem, integrating multiple self-supervised and knowledge distillation proxy tasks in a single architecture.
Ranked #2 on
Anomaly Detection
on UCSD Peds2
Abnormal Event Detection In Video
Anomaly Detection In Surveillance Videos
+4
1 code implementation • NeurIPS 2020 • Antonio Barbalau, Adrian Cosma, Radu Tudor Ionescu, Marius Popescu
To generate useful data samples for training the student, our framework (i) learns to generate images on a proxy data set (with images and classes different from those used to train the black-box) and (ii) applies an evolutionary strategy to make sure that each generated data sample exhibits a high response for a specific class when given as input to the black box.
no code implementations • 14 Oct 2020 • Nicolae-Cătălin Ristea, Andrei Anghel, Radu Tudor Ionescu, Yonina C. Eldar
In autonomous driving, radar systems play an important role in detecting targets such as other vehicles on the road.
no code implementations • VarDial (COLING) 2020 • Mihaela Gaman, Radu Tudor Ionescu
From simple models for regression, such as Support Vector Regression, to deep neural networks, such as Long Short-Term Memory networks and character-level convolutional neural networks, and, finally, to ensemble models based on meta-learners, such as XGBoost, our interest is focused on approaching the problem from a few different perspectives, in an attempt to minimize the prediction error.
no code implementations • 25 Sep 2020 • Adrian Sandru, Georgian-Emilian Duta, Mariana-Iuliana Georgescu, Radu Tudor Ionescu
Typical approaches for PPE detection based on deep learning are (i) to train an object detector for items such as those listed above or (ii) to train a person detector and a classifier that takes the bounding boxes predicted by the detector and discriminates between people wearing and people not wearing the corresponding PPE items.
no code implementations • 2 Sep 2020 • Cezara Benegui, Radu Tudor Ionescu
In this study, we focus on deep learning methods for explicit authentication based on motion sensor signals.
no code implementations • 1 Sep 2020 • Cezara Benegui, Radu Tudor Ionescu
In order to prevent some of the possible attacks, these explicit authentication systems can be enhanced by considering a two-factor authentication scheme, in which the second factor is an implicit authentication system based on analyzing motion sensor data captured by accelerometers or gyroscopes.
2 code implementations • 27 Aug 2020 • Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Fahad Shahbaz Khan, Marius Popescu, Mubarak Shah
Following the standard formulation of abnormal event detection as outlier detection, we propose a background-agnostic framework that learns from training videos containing only normal events.
Abnormal Event Detection In Video
Anomaly Detection In Surveillance Videos
+2
1 code implementation • 11 Aug 2020 • Nicolae-Cătălin Ristea, Andrei Anghel, Radu Tudor Ionescu
In order to train our network in a real-world scenario, we introduce a new data set of realistic automotive radar signals with multiple targets and multiple interferers.
no code implementations • 3 Aug 2020 • Mariana-Iuliana Georgescu, Radu Tudor Ionescu
First of all, we employ the classic teacher-student training strategy, in which the teacher is a CNN trained on fully-visible faces and the student is a CNN trained on occluded faces.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
1 code implementation • 1 Aug 2020 • Mihail Burduja, Radu Tudor Ionescu, Nicolae Verga
In this paper, we present our system for the RSNA Intracranial Hemorrhage Detection challenge.
1 code implementation • 30 Jul 2020 • Mihaela Găman, Radu Tudor Ionescu
We conduct a subjective evaluation by human annotators, showing that humans attain much lower accuracy rates compared to machine learning (ML) models.
1 code implementation • 21 Jul 2020 • Nicolae-Cătălin Ristea, Andrei Anghel, Radu Tudor Ionescu
Moreover, considering the lack of databases for this task, we release as open source a large scale data set that closely replicates real world automotive scenarios for single-interference cases, allowing others to objectively compare their future work in this domain.
Signal Processing
no code implementations • 17 Jun 2020 • Nicolae-Cătălin Ristea, Radu Tudor Ionescu
Original and translated utterances are converted into spectrograms which are provided as input to a set of ResNet neural networks with various depths.
1 code implementation • 6 Jun 2020 • Antonio Barbalau, Adrian Cosma, Radu Tudor Ionescu, Marius Popescu
In this work, we focus on explainable AI and propose a novel generic and model-agnostic framework for synthesizing input exemplars that maximize a desired response from a machine learning model.
1 code implementation • 2 Feb 2020 • Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Nicolae-Catalin Ristea, Nicu Sebe
In order to classify linearly non-separable data, neurons are typically organized into multi-layer neural networks that are equipped with at least one hidden layer.
Ranked #7 on
Speech Emotion Recognition
on CREMA-D
1 code implementation • 5 Jan 2020 • Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Nicolae Verga
We evaluate our method in the context of 2D and 3D super-resolution of CT and MRI scans from two databases, comparing it to relevant related works from the literature and baselines based on various interpolation schemes, using 2x and 4x scaling factors.
Ranked #6 on
Image Super-Resolution
on IXI
no code implementations • 8 Dec 2019 • Cezara Benegui, Radu Tudor Ionescu
To pre-train the CNN and the RNN models for multi-class user classification, we use a different set of users than the set used for few-shot user identification, ensuring a realistic scenario.
no code implementations • 4 Dec 2019 • Sébastien Déjean, Radu Tudor Ionescu, Josiane Mothe, Md Zia Ullah
We found that: (1) our model based on a limited number of selected features is as good as more complex models for QPP and better than non-selective models; (2) our model is more efficient than complex models during inference time since it requires fewer features; (3) the predictive model is readable and understandable; and (4) one of our new QPP features is consistently selected across different collections, proving its usefulness.
no code implementations • 15 Nov 2019 • Petru Soviany, Radu Tudor Ionescu, Paolo Rota, Nicu Sebe
To alleviate this problem, researchers proposed various domain adaptation methods to improve object detection results in the cross-domain setting, e. g. by translating images with ground-truth labels from the source domain to the target domain using Cycle-GAN.
no code implementations • 12 Nov 2019 • Mariana-Iuliana Georgescu, Radu Tudor Ionescu
In this paper, we present an approach based on convolutional neural networks (CNNs) for facial expression recognition in a difficult setting with severe occlusions.
Facial Expression Recognition
Facial Expression Recognition (FER)
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 • WS 2019 • Marcos Zampieri, Shervin Malmasi, Yves Scherrer, Tanja Samard{\v{z}}i{\'c}, Francis Tyers, Miikka Silfverberg, Natalia Klyueva, Tung-Le Pan, Chu-Ren Huang, Radu Tudor Ionescu, Andrei M. Butnaru, Tommi Jauhiainen
In this paper, we present the findings of the Third VarDial Evaluation Campaign organized as part of the sixth edition of the workshop on Natural Language Processing (NLP) for Similar Languages, Varieties and Dialects (VarDial), co-located with NAACL 2019.
no code implementations • 2 May 2019 • Mariana-Iuliana Georgescu, Radu Tudor Ionescu
We propose a novel agglomerative clustering method based on unmasking, a technique that was previously used for authorship verification of text documents and for abnormal event detection in videos.
1 code implementation • NAACL 2019 • Radu Tudor Ionescu, Andrei M. Butnaru
The Vector of Locally-Aggregated Word Embeddings (VLAWE) representation of a document is then computed by accumulating the differences between each codeword vector and each word vector (from the document) associated to the respective codeword.
Ranked #1 on
Sentiment Analysis
on MR
1 code implementation • ACL 2019 • Andrei M. Butnaru, Radu Tudor Ionescu
In this work, we introduce the MOldavian and ROmanian Dialectal COrpus (MOROCO), which is freely available for download at https://github. com/butnaruandrei/MOROCO.
1 code implementation • CVPR 2019 • Radu Tudor Ionescu, Fahad Shahbaz Khan, Mariana-Iuliana Georgescu, Ling Shao
Most existing approaches formulate abnormal event detection as an outlier detection task, due to the scarcity of anomalous data during training.
Ranked #14 on
Anomaly Detection
on ShanghaiTech
no code implementations • 27 Nov 2018 • Petru Soviany, Radu Tudor Ionescu
All the approaches are based on separating the test images in two batches, an easy batch that is fed to a faster face detector and a difficult batch that is fed to a more accurate yet slower detector.
no code implementations • 2 Nov 2018 • Radu Tudor Ionescu, Andrei M. Butnaru
Although classifiers for a target domain can be trained on labeled text data from a related source domain, the accuracy of such classifiers is usually lower in the cross-domain setting.
no code implementations • EMNLP 2018 • Radu Tudor Ionescu, Andrei M. Butnaru
Instead, we use the labels predicted by the classifier in the first training iteration.
1 code implementation • 29 May 2018 • Paul Andrei Bricman, Radu Tudor Ionescu
It is important to note that we have to train an individual neural network for each input image, i. e. one network encodes a single image only.
no code implementations • COLING 2018 • Andrei M. Butnaru, Radu Tudor Ionescu
Furthermore, our top macro-F1 score (58. 92%) is significantly better than the second best score (57. 59%) in the 2018 ADI Shared Task, according to the statistical significance test performed by the organizers.
no code implementations • 29 Apr 2018 • Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Marius Popescu
We present an approach that combines automatic features learned by convolutional neural networks (CNN) and handcrafted features computed by the bag-of-visual-words (BOVW) model in order to achieve state-of-the-art results in facial expression recognition.
Ranked #4 on
Facial Expression Recognition (FER)
on FER2013
(using extra training data)
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
no code implementations • ACL 2018 • Mădălina Cozma, Andrei M. Butnaru, Radu Tudor Ionescu
In this work, we present an approach based on combining string kernels and word embeddings for automatic essay scoring.
Ranked #3 on
Automated Essay Scoring
on ASAP
no code implementations • 23 Mar 2018 • Petru Soviany, Radu Tudor Ionescu
The image difficulty predictor is applied on the test images to split them into easy versus hard images.
no code implementations • WS 2018 • Andrei M. Butnaru, Radu Tudor Ionescu
In this paper, we present a kernel-based learning approach for the 2018 Complex Word Identification (CWI) Shared Task.
no code implementations • 3 Mar 2018 • Sorina Smeureanu, Radu Tudor Ionescu
Recent terrorist attacks in major cities around the world have brought many casualties among innocent citizens.
no code implementations • 12 Jan 2018 • Radu Tudor Ionescu, Sorina Smeureanu, Marius Popescu, Bogdan Alexe
To detected abnormal events in the test video, we analyze each test sample and consider its maximum normality score provided by the trained one-class SVM models, based on the intuition that a test sample can belong to only one cluster of normality.
Ranked #15 on
Anomaly Detection
on CUHK Avenue
no code implementations • WS 2017 • Radu Tudor Ionescu, Marius Popescu
While most of our kernels are based on character p-grams (also known as n-grams) extracted from essays or speech transcripts, we also use a kernel based on i-vectors, a low-dimensional representation of audio recordings, provided by the shared task organizers.
no code implementations • 25 Jul 2017 • Andrei M. Butnaru, Radu Tudor Ionescu
In this paper, we propose a novel approach for text classification based on clustering word embeddings, inspired by the bag of visual words model, which is widely used in computer vision.
no code implementations • EACL 2017 • Andrei M. Butnaru, Radu Tudor Ionescu, Florentina Hristea
In this paper, we present a novel unsupervised algorithm for word sense disambiguation (WSD) at the document level.
Ranked #8 on
Word Sense Disambiguation
on SemEval 2007 Task 7
no code implementations • ICCV 2017 • Radu Tudor Ionescu, Sorina Smeureanu, Bogdan Alexe, Marius Popescu
We propose a novel framework for abnormal event detection in video that requires no training sequences.
Ranked #29 on
Anomaly Detection
on CUHK Avenue
Abnormal Event Detection In Video
Authorship Verification
+1
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 • WS 2017 • Radu Tudor Ionescu, Andrei Butnaru
We present a machine learning approach for the Arabic Dialect Identification (ADI) and the German Dialect Identification (GDI) Closed Shared Tasks of the DSL 2017 Challenge.
no code implementations • WS 2016 • Radu Tudor Ionescu, Marius Popescu
Our approach is shallow and simple, but the empirical results obtained in the ADI Shared Task prove that it achieves very good results.