Radu Tudor Ionescu

XMAD-Bench: Cross-Domain Multilingual Audio Deepfake Benchmark EACL 2026 Text Classification Under Class Distribution Shift: A Survey EACL 2026 ExDDV: A New Dataset for Explainable Deepfake Detection in Video WACV 2026 AutoMalDesc: Large-Scale Script Analysis for Cyber Threat Research AAAI 2026 Multi-Level Feature Distillation of Joint Teachers Trained on Distinct Image Datasets WACV 2025 DLCR: A Generative Data Expansion Framework via Diffusion for Clothes-Changing Person Re-ID WACV 2025 Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Text ACL 2025 Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers WACV 2025 RipVIS: Rip Currents Video Instance Segmentation Benchmark for Beach Monitoring and Safety CVPR 2025 Curriculum Direct Preference Optimization for Diffusion and Consistency Models CVPR 2025 PQPP: A Joint Benchmark for Text-to-Image Prompt and Query Performance Prediction CVPR 2025 VarDial Evaluation Campaign 2024: Commonsense Reasoning in Dialects and Multi-Label Similar Language Identification NAACL 2024 CL-MAE: Curriculum-Learned Masked Autoencoders WACV 2024 UnibucLLM: Harnessing LLMs for Automated Prediction of Item Difficulty and Response Time for Multiple-Choice Questions NAACL 2024 RoDia: A New Dataset for Romanian Dialect Identification from Speech NAACL 2024 Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors CVPR 2024 A Novel Cartography-Based Curriculum Learning Method Applied on RoNLI: The First Romanian Natural Language Inference Corpus ACL 2024 Multimodal Multi-Head Convolutional Attention With Various Kernel Sizes for Medical Image Super-Resolution WACV 2023 Audiovisual Masked Autoencoders ICCV 2023 A Novel Contrastive Learning Method for Clickbait Detection on RoCliCo: A Romanian Clickbait Corpus of News Articles EMNLP 2023 SepTr: Separable Transformer for Audio Spectrogram Processing INTERSPEECH 2022 VeriDark: A Large-Scale Benchmark for Authorship Verification on the Dark Web NIPS 2022 Findings of the VarDial Evaluation Campaign 2022 COLING 2022 Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection CVPR 2022 UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection CVPR 2022 Rethinking the Authorship Verification Experimental Setups EMNLP 2022 SuPEr-SAM: Using the Supervision Signal From a Pose Estimator to Train a Spatial Attention Module for Personal Protective Equipment Recognition WACV 2021 Findings of the VarDial Evaluation Campaign 2021 EACL 2021 Clustering Word Embeddings with Self-Organizing Maps. Application on LaRoSeDa - A Large Romanian Sentiment Data Set EACL 2021 Anomaly Detection in Video via Self-Supervised and Multi-Task Learning CVPR 2021 SaRoCo: Detecting Satire in a Novel Romanian Corpus of News Articles IJCNLP 2021 SaRoCo: Detecting Satire in a Novel Romanian Corpus of News Articles ACL 2021 Self-Paced Ensemble Learning for Speech and Audio Classification INTERSPEECH 2021 UnibucKernel: Geolocating Swiss German Jodels Using Ensemble Learning EACL 2021 Are you Wearing a Mask? Improving Mask Detection from Speech Using Augmentation by Cycle-Consistent GANs INTERSPEECH 2020 A Report on the VarDial Evaluation Campaign 2020 COLING 2020 Combining Deep Learning and String Kernels for the Localization of Swiss German Tweets COLING 2020 Black-Box Ripper: Copying black-box models using generative evolutionary algorithms NIPS 2020 Image Difficulty Curriculum for Generative Adversarial Networks (CuGAN) WACV 2020 Vector of Locally-Aggregated Word Embeddings (VLAWE): A Novel Document-level Representation NAACL 2019 Object-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in Video CVPR 2019 MOROCO: The Moldavian and Romanian Dialectal Corpus ACL 2019 A Report on the Third VarDial Evaluation Campaign NAACL 2019 UnibucKernel: A kernel-based learning method for complex word identification NAACL 2018 Automated essay scoring with string kernels and word embeddings ACL 2018 Improving the results of string kernels in sentiment analysis and Arabic dialect identification by adapting them to your test set EMNLP 2018 UnibucKernel Reloaded: First Place in Arabic Dialect Identification for the Second Year in a Row COLING 2018 Unmasking the Abnormal Events in Video ICCV 2017 ShotgunWSD: An unsupervised algorithm for global word sense disambiguation inspired by DNA sequencing EACL 2017 How Hard Can It Be? Estimating the Difficulty of Visual Search in an Image CVPR 2016 Can characters reveal your native language? A language-independent approach to native language identification EMNLP 2014