Search Results for author:
Found 96 papers, 38 papers with code
Findings of the VarDial Evaluation Campaign 2022
This report presents the results of the shared tasks organized as part of the VarDial Evaluation Campaign 2022.
Findings of the VarDial Evaluation Campaign 2021
This paper describes the results of the shared tasks organized as part of the VarDial Evaluation Campaign 2021.
A Report on the VarDial Evaluation Campaign 2020
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.
UnibucLLM: Harnessing LLMs for Automated Prediction of Item Difficulty and Response Time for Multiple-Choice Questions
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.
Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers
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.
Cascaded Cross-Modal Transformer for Audio-Textual Classification
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
Sea-Land-Cloud Segmentation in Satellite Hyperspectral Imagery by Deep Learning
Satellites are increasingly adopting on-board AI for enhanced autonomy through in-orbit inference.
A Novel Contrastive Learning Method for Clickbait Detection on RoCliCo: A Romanian Clickbait Corpus of News Articles
Despite the importance of the task, to the best of our knowledge, there is no publicly available clickbait corpus for the Romanian language.
Towards Few-Call Model Stealing via Active Self-Paced Knowledge Distillation and Diffusion-Based Image Generation
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.
Learning Using Generated Privileged Information by Text-to-Image Diffusion Models
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.
RoDia: A New Dataset for Romanian Dialect Identification from Speech
We introduce RoDia, the first dataset for Romanian dialect identification from speech.
CL-MAE: Curriculum-Learned Masked Autoencoders
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.
JEDI: Joint Expert Distillation in a Semi-Supervised Multi-Dataset Student-Teacher Scenario for Video Action Recognition
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.
Reverse Stable Diffusion: What prompt was used to generate this image?
Our novel learning framework produces excellent results on the aforementioned task, yielding the highest gains when applied on the white-box model.
Cascaded Cross-Modal Transformer for Request and Complaint Detection
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
Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors
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
Class Anchor Margin Loss for Content-Based Image Retrieval
The performance of neural networks in content-based image retrieval (CBIR) is highly influenced by the chosen loss (objective) function.
iQPP: A Benchmark for Image Query Performance Prediction
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.
FreCDo: A Large Corpus for French Cross-Domain Dialect Identification
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.
Audiovisual Masked Autoencoders
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)
Lightning Fast Video Anomaly Detection via Adversarial Knowledge Distillation
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
Diversity-Promoting Ensemble for Medical Image Segmentation
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.
Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection
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
Diffusion Models in Vision: A Survey
Denoising diffusion models represent a recent emerging topic in computer vision, demonstrating remarkable results in the area of generative modeling.
SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection
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
VeriDark: A Large-Scale Benchmark for Authorship Verification on the Dark Web
The DarkWeb represents a hotbed for illicit activity, where users communicate on different market forums in order to exchange goods and services.
LeRaC: Learning Rate Curriculum
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
Multimodal Multi-Head Convolutional Attention with Various Kernel Sizes for Medical Image Super-Resolution
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
SepTr: Separable Transformer for Audio Spectrogram Processing
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
Discriminability-enforcing loss to improve representation learning
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.
Feature-level augmentation to improve robustness of deep neural networks to affine transformations
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.
Self-paced learning to improve text row detection in historical documents with missing labels
An important preliminary step of optical character recognition systems is the detection of text rows.
Teacher-Student Training and Triplet Loss to Reduce the Effect of Drastic Face Occlusion
To this end, we study two knowledge distillation methods, one based on teacher-student training and one based on triplet loss.
Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection
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)
UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection
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)
CyTran: A Cycle-Consistent Transformer with Multi-Level Consistency for Non-Contrast to Contrast CT Translation
Our neural model can be trained on unpaired images, due to the integration of a multi-level cycle-consistency loss.
A realistic approach to generate masked faces applied on two novel masked face recognition data sets
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
Contextual Convolutional Neural Networks
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
Improving the Authentication with Built-in Camera Protocol Using Built-in Motion Sensors: A Deep Learning Solution
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%.
SaRoCo: Detecting Satire in a Novel Romanian Corpus of News Articles
In this work, we introduce a corpus for satire detection in Romanian news.
FreSaDa: A French Satire Data Set for Cross-Domain Satire Detection
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).
Clustering Word Embeddings with Self-Organizing Maps. Application on LaRoSeDa - A Large Romanian Sentiment Data Set
Romanian is one of the understudied languages in computational linguistics, with few resources available for the development of natural language processing tools.
Self-paced ensemble learning for speech and audio classification
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
Unsupervised Medical Image Alignment with Curriculum Learning
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.
UnibucKernel: Geolocating Swiss German Jodels Using Ensemble Learning
In this work, we describe our approach addressing the Social Media Variety Geolocation task featured in the 2021 VarDial Evaluation Campaign.
Curriculum Learning: A Survey
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.
Clustering Word Embeddings with Self-Organizing Maps. Application on LaRoSeDa -- A Large Romanian Sentiment Data Set
Romanian is one of the understudied languages in computational linguistics, with few resources available for the development of natural language processing tools.
Natural vs Balanced Distribution in Deep Learning on Whole Slide Images for Cancer Detection
The class distribution of data is one of the factors that regulates the performance of machine learning models.
Anomaly Detection in Video via Self-Supervised and Multi-Task Learning
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
Black-Box Ripper: Copying black-box models using generative evolutionary algorithms
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.
Automotive Radar Interference Mitigation with Unfolded Robust PCA based on Residual Overcomplete Auto-Encoder Blocks
In autonomous driving, radar systems play an important role in detecting targets such as other vehicles on the road.
Combining Deep Learning and String Kernels for the Localization of Swiss German Tweets
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.
SuPEr-SAM: Using the Supervision Signal from a Pose Estimator to Train a Spatial Attention Module for Personal Protective Equipment Recognition
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.
Adversarial Attacks on Deep Learning Systems for User Identification based on Motion Sensors
In this study, we focus on deep learning methods for explicit authentication based on motion sensor signals.
To augment or not to augment? Data augmentation in user identification based on motion sensors
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.
A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video
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
Estimating the Magnitude and Phase of Automotive Radar Signals under Multiple Interference Sources with Fully Convolutional Networks
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.
Teacher-Student Training and Triplet Loss for Facial Expression Recognition under Occlusion
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
Accurate and Efficient Intracranial Hemorrhage Detection and Subtype Classification in 3D CT Scans with Convolutional and Long Short-Term Memory Neural Networks
In this paper, we present our system for the RSNA Intracranial Hemorrhage Detection challenge.
The Unreasonable Effectiveness of Machine Learning in Moldavian versus Romanian Dialect Identification
We conduct a subjective evaluation by human annotators, showing that humans attain much lower accuracy rates compared to machine learning (ML) models.
Fully Convolutional Neural Networks for Automotive Radar Interference Mitigation
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
Are you wearing a mask? Improving mask detection from speech using augmentation by cycle-consistent GANs
Original and translated utterances are converted into spectrograms which are provided as input to a set of ResNet neural networks with various depths.
A Generic and Model-Agnostic Exemplar Synthetization Framework for Explainable AI
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.
Non-linear Neurons with Human-like Apical Dendrite Activations
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
Convolutional Neural Networks with Intermediate Loss for 3D Super-Resolution of CT and MRI Scans
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
Convolutional Neural Networks for User Identificationbased on Motion Sensors Represented as Image
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.
Forward and Backward Feature Selection for Query Performance Prediction
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.
Curriculum Self-Paced Learning for Cross-Domain Object Detection
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.
Recognizing Facial Expressions of Occluded Faces using Convolutional Neural Networks
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)
Image Difficulty Curriculum for Generative Adversarial Networks (CuGAN)
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
A Report on the Third VarDial Evaluation Campaign
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.
Clustering Images by Unmasking - A New Baseline
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.
Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation
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
MOROCO: The Moldavian and Romanian Dialectal Corpus
In this work, we introduce the MOldavian and ROmanian Dialectal COrpus (MOROCO), which is freely available for download at https://github. com/butnaruandrei/MOROCO.
Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video
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
Continuous Trade-off Optimization between Fast and Accurate Deep Face Detectors
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.
Transductive Learning with String Kernels for Cross-Domain Text Classification
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.
Improving the results of string kernels in sentiment analysis and Arabic dialect identification by adapting them to your test set
Instead, we use the labels predicted by the classifier in the first training iteration.
CocoNet: A deep neural network for mapping pixel coordinates to color values
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.
UnibucKernel Reloaded: First Place in Arabic Dialect Identification for the Second Year in a Row
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.
Local Learning with Deep and Handcrafted Features for Facial Expression Recognition
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
Automated essay scoring with string kernels and word embeddings
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
Optimizing the Trade-off between Single-Stage and Two-Stage Object Detectors using Image Difficulty Prediction
The image difficulty predictor is applied on the test images to split them into easy versus hard images.
UnibucKernel: A kernel-based learning method for complex word identification
In this paper, we present a kernel-based learning approach for the 2018 Complex Word Identification (CWI) Shared Task.
Real-Time Deep Learning Method for Abandoned Luggage Detection in Video
Recent terrorist attacks in major cities around the world have brought many casualties among innocent citizens.
Detecting abnormal events in video using Narrowed Normality Clusters
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
Can string kernels pass the test of time in Native Language Identification?
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.
From Image to Text Classification: A Novel Approach based on Clustering Word Embeddings
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.
ShotgunWSD: An unsupervised algorithm for global word sense disambiguation inspired by DNA sequencing
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
Unmasking the abnormal events in video
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
How hard can it be? Estimating the difficulty of visual search in an image
We address the problem of estimating image difficulty defined as the human response time for solving a visual search task.
Learning to Identify Arabic and German Dialects using Multiple Kernels
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.
UnibucKernel: An Approach for Arabic Dialect Identification Based on Multiple String Kernels
Our approach is shallow and simple, but the empirical results obtained in the ADI Shared Task prove that it achieves very good results.
