Marcella Astrid, Abdelrahman Shabayek, and Djamila Aouada. “Zero-Shot Anomaly Detection in Battery Thermal Images Using Visual Question Answering with Prior Knowledge”. In: 33rd European Signal Processing Conference (EUSIPCO). Sep. 8–12, 2025. [Arxiv] (Accepted)
Marcella Astrid, Muhammad Zaigham Zaheer, Djamila Aouada, and Seung-Ik Lee. "Exploiting Autoencoder's Weakness to Generate Pseudo Anomalies". Neural Computing and Applications (2024). https://doi.org/10.1007/s00521-024-09790-z. [Paper] [Arxiv]
Marcella Astrid, Muhammad Zaigham Zaheer, and Seung-Ik Lee. "PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomalies". Neurocomputing 534 (2023):147-160. [Elsevier_Link] [Preprint]
Marcella Astrid, Muhammad Zaigham Zaheer, Jae-Yeong Lee, and Seung-Ik Lee. “Learning Not to Reconstruct Anomalies”. In: British Machine Vision Conference 2021(BMVC2021) (Virtual). Nov. 22–25, 2021. [Paper] [Code] [Video]
Marcella Astrid, Muhammad Zaigham Zaheer, and Seung-Ik Lee. “Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detection”. In: International Conference on Computer Vision (ICCV 2021) Workshop (Virtual). Oct. 11–17, 2021. [Paper] [Code] [Video]
Muhammad Zaigham Zaheer, Jin-ha Lee, Marcella Astrid, and Seung-Ik Lee. "Old is Gold: Redefining the adversarially learned one-class classier training paradigm". In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (On-line). June 14-19, 2020, pp. 14183-14193. (h-5 index(2020): 299). [Link]
Muhammad Zaigham Zaheer, Arif Mahmood, Marcella Astrid, and Seung-Ik Lee. "CLAWS: Clustering assisted weakly supervised learning with normalcy suppression for anomalous event detection". In: European Conference on Computer Vision (ECCV) (On-line). Aug. 23-28, 2020, pp. 4489-4497. (h-5 index(2020): 176). [Link]
Marcella Astrid, Muhammad Zaigham Zaheer, and Seung-Ik Lee. "Constricting Normal Latent Space for Anomaly Detection with Normal-only Training Data". In: The International Conference on Learning Representations (ICLR) Workshop (Practical ML for Low Resource Settings (PML4LRS)). May 11, 2024. [Arxiv] (Presented, not published)
Marcella Astrid, Muhammad Zaigham Zaheer, and Seung-Ik Lee. "Improving Anomaly Detection Model Using Prior Knowledge". In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). June 19-24, 2022. [Link] (Presented, not published)
Marcella Astrid and Seung-Ik Lee. “Generalizing Skipping Frame Pseudo Anomaly Based Anomaly Detection Into Prediction Task”. In: The 32nd Joint Conference on Communications and Information (JCCI 2022) (Sokcho, Korea). April 27–29, 2022. [Paper] [Video]
Marcella Astrid, Muhammad Zaigham Zaheer, and Seung-Ik Lee. "Limiting Reconstruction Capability of Autoencoders Using Moving Backward Pseudo Anomalies". In: The 19th International Conference on Ubiquitous Robots (UR 2022) (Jeju, Korea). July 4-6, 2022. [Paper] [Video]
Marcella Astrid and Seung-Ik Lee. “Using Pseudo Anomalies to Train a Binary Classifier for Anomaly Detection”. In: Korea Software Congress 2022 (KSC 2022) (Jeju, Korea). Dec. 20–23, 2022, pp. 818–820. [Link]
Marcella Astrid, Minsu Jang, and Seung-Ik Lee. “Improving Discriminative Capability of Anomaly Detector using Pseudo Anomalies and Triplet Loss”. In: KICS Winter Conference 2023 (KICS 2023) (PyeongChang, Korea). Feb. 8–10, 2023. [Link]
Muhammad Zaigham Zaheer, Jin-ha Lee, Marcella Astrid, Arif Mahmood, and Seung-Ik Lee. "Cleaning label noise with clusters for minimally supervised anomaly detection". In: IEEE Conference on Computer Vision and Pattern Recognition Workshops(CVPRW) (On-line). June 14-19, 2020. (h-5 index(2020): 299). [Link] (Presented, not published)
Seung-Ik Lee, Jinha Lee, Marcella Astrid, and Muhammad Zaigham Zaheer. “Fighting Against Data Deficiency Problems for Surveillance”. In: 2021 The 21st International Conference on Control, Automation and Systems (ICCAS 2021) Workshop (Ramada Plaza Hotel, Jeju, Korea). Oct. 12–15, 2021. [Link]
Muhammad Zaigham Zaheer, Marcella Astrid, and Seung-Ik Lee. “Detecting Change to Quantify Anomalies for Robust Outdoor Surveillance”. In: 2021 The 21st International Conference on Control, Automation and Systems (ICCAS 2021) Workshop (Ramada Plaza Hotel, Jeju, Korea). Oct. 12–15, 2021. [Link]
Muhammad Zaigham Zaheer, Marcella Astrid, and Seung-Ik Lee. “The Effects of Randomizing Input Feature Vectors When Training Video Based Learning Models”. In: Korea Computer Congress 2021 (KCC 2021) (Jeju, Korea). June 23–25, 2021, pp. 654–656. [Link]
Muhammad Zaigham Zaheer, Arif Mahmood, Marcella Astrid, Haris Khan, and Seung-Ik Lee. “An Anomaly Detection System via Moving Surveillance Robots with Human Collaboration”. In: International Conference on Computer Vision (ICCV 2021) Workshop (Virtual). Oct. 11–17, 2021. [Link]
Jin-ha Lee, Marcella Astrid, Muhammad Zaigham Zaheer, and Seung-Ik Lee. "Deep visual anomaly detection with negative learning". In: The 27th International Workshop on Frontiers of Computer Vision (IWFCV 2021) (On-line). Feb. 22-23, 2021. [Link]
Muhammad Zaigham Zaheer, Marcella Astrid, Seung-Ik Lee, and Ho Chul Shin. "Ensemble grid formation to detect potential anomalous regions using context encoders". In: International Conference on Control, Automation and Systems (ICCAS) (PyeongChang, Korea). Oct. 17-20, 2018. [Link]
Muhammad Zaigham Zaheer, Jin Ha Lee, Arif Mahmood, Marcella Astrid, and Seung-Ik Lee. “Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomalies”. In: IEEE Transactions on Image Processing 31 (2022): 5963-5975. [Link] [IEEE_Link]
Muhammad Zaigham Zaheer, Arif Mahmood, Marcella Astrid, and Seung-Ik Lee. “Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos”. In: IEEE Transactions on Neural Networks and Learning Systems (2023). [Preprint] [IEEE_Link]
Marcella Astrid, Enjie Ghorbel, and Djamila Aouada. “Audio-visual Deepfake Detection With Local Temporal Inconsistencies”. In: 2025 International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2025). Apr. 6–11, 2025. [Arxiv]
Marcella Astrid, Enjie Ghorbel, and Djamila Aouada. “Detecting Audio-Visual Deepfakes with Fine-Grained Inconsistencies”. In: The Thirty Fifth British Machine Vision Conference (BMVC 2024). Nov. 25–28, 2024. [Arxiv] [Paper] [Code]
Marcella Astrid, Enjie Ghorbel, and Djamila Aouada. “Statistic-aware Audio-visual Deepfake Detector”. In: 2024 IEEE International Conference on Image Processing (ICIP 2024). Oct. 27–30, 2024. [Arxiv] [Paper] [Code]
Marcella Astrid, Enjie Ghorbel, and Djamila Aouada. “Targeted Augmented Data for Audio Deepfake Detection”. In: 32nd European Signal Processing Conference (EUSIPCO). Aug. 26–30, 2024. [Arxiv] [Paper] [Code]
Dat Nguyen, Marcella Astrid, Anis Kacem, Enjie Ghorbel, and Djamila Aouada. “Vulnerability-Aware Spatio-Temporal Learning for Generalizable Deepfake Video Detection”. In: International Conference on Computer Vision (ICCV). Oct. 19-23, 2025. [Arxiv] (Accepted)
Dat Nguyen, Nesryne Mejri, Inder Pal Singh, Polina Kuleshova, Marcella Astrid, Anis Kacem, Enjie Ghorbel, and Djamila Aouada. "LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection". In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 17-21, 2024. [Arxiv] [Code] [CVF]
Marcella Astrid and Seung-Ik Lee. "Assembling three one-camera images for three-camera intersection classification". ETRI Journal, 45(5) (Oct. 2023), pp.862-873. [Link]
Marcella Astrid and Seung-Ik Lee. “Constructing Three-Camera Data with One-Camera Data for Intersection Detection”. In: Conference on Information and Control Systems (CICS 2022) Workshop (PyeongChang, Korea). Oct. 19–22, 2022. [Link]
Marcella Astrid, Jin-Ha Lee, Muhammad Zaigham Zaheer, Jae-Yeong Lee, and Seung-Ik Lee. "For safer navigation: Pedestrian-view intersection classification". In: International Conference on ICT Convergence (ICTC) (Jeju, Korea). Oct. 21-23, 2020. [Link]
Marcella Astrid, Muhammad Zaigham Zaheer, Jin-Ha Lee, Jae-Yeong Lee, and Seung-Ik Lee. "What do pedestrians see?: Visualizing pedestrian-view intersection classification". In: International Conference on Control, Automation and Systems (ICCAS) (Online). Oct. 13-16, 2020, pp. 769-773. [Paper] [Video]
Marcella Astrid, Muhammad Zaigham Zaheer, Jae-Yeong Lee, and Seung-Ik Lee. “Domain-Robust Pedestrian-View Intersection Classification”. In: The 12th International Conference on Information and Communication Technology Convergence (ICTC 2021) (Ramada Plaza Hotel, Jeju, Korea). Oct. 20–22, 2021. [Paper] [Video]
Marcella Astrid, Muhammad Zaigham Zaheer, and Seung-Ik Lee. “Intra-Batch Features Separation for Indoor and Outdoor Pedestrian-View Intersection Classification”. In: 2021 The 21st International Conference on Control, Automation and Systems (ICCAS 2021) (Ramada Plaza Hotel, Jeju, Korea). Oct. 12–15, 2021. [Paper] [Video]
Marcella Astrid, Muhammad Zaigham Zaheer, and Seung-Ik Lee. “The Comparisons of Different Base Networks for Pedestrian-View Intersection Classification”. In: Korea Software Congress 2021 (KSC 2021) (PyeongChang, Korea). Dec. 20–22, 2021, pp. 685–687. [Link]
Marcella Astrid, Muhammad Zaigham Zaheer, and Seung-Ik Lee. “Comparisons of Domain-Removal Losses in Multi-Domain Pedestrian-View Intersection Classification”. In: 2nd Korea Artificial Intelligence Conference (Jeju, Korea). Sept. 29–Oct. 1, 2021, pp. 349–350. [Link]
Marcella Astrid, Muhammad Zaigham Zaheer, and Seung-Ik Lee. “The Importance of ImageNet-Pretrained Network on Pedestrian-View Intersection Classification”. In: 2021 The Institute of Electronics and Information Engineers Summer Conference (IEIE2021) (Jeju, Korea). June 30–July 2, 2021, pp. 1565–1568. [Link]
Marcella Astrid and Seung-Ik Lee. "Utilizing One-Camera Data for Three-Camera Intersection Classification". In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). June 19-24, 2022. [Link] (Presented, not published)
Jeong-Seon Lim, Marcella Astrid, Hyun-Jin Yoon, and Seung-Ik Lee. "Small object detection using context and attention". In: International Conference on Artificial Intelligence in Information Communication (ICAIIC 2021) (Jeju, Korea). Apr. 13-16, 2021, pp. 181-186. [Paper] [Video]
Marcella Astrid, Seung-Ik Lee, and Beom-Su Seo. "Speeding-up multiple object tracking by frame skipping". In: Korea Computer Congress (KCC) (Jeju, Korea). June 20-22, 2018, pp. 864-866. [Link]
Assefa Seyoum Wahd, Marcella Astrid, and Seung-Ik Lee. “Low-Likelihood EBM Samples for Out-of-Distribution Detection”. In: 35th Workshop on Image Processing and Image Understanding (IPIU 2023). [Link]
Jin-ha Lee, Muhammad Zaigham Zaheer, Marcella Astrid, and Seung-Ik Lee. "SmoothMix: A simple yet effective data augmentation to train robust classifiers". In: IEEE Conference on Computer Vision and Pattern Recognition Workshop on Deep Vision (CVPRW) (On-line). June 14-19, 2020. (h-5 index(2020): 299). [Link]
Marcella Astrid and Seung-Ik Lee. “The Comparisons of Boundary Data Generation for Semi-Supervised Learning in Image Classification”. In: 3rd Korea Artificial Intelligence Conference (Korea AI 2022) (Jeju, Korea). Sept. 28–30, 2022. [Link]
Marcella Astrid, Muhammad Zaigham Zaheer, and Seung-Ik Lee. “Semi-Supervised Learning Using Data Between Real and Noise”. In: KICS Winter Conference 2022 (KICS 2022) (PyeongChang, Korea). Feb. 9–11, 2022, pp. 545–546. [Link]
Marcella Astrid and Seung-Ik Lee. "Cp-decomposition with tensor power method for convolutional neural networks compression". In: IEEE International Conference on Big Data and Smart Computing (BigComp) (Jeju, Korea). Feb. 13-16, 2017, pp. 115-118. [Link]
Marcella Astrid and Seung-Ik Lee. "Deep compression of convolutional neural networks with low-rank approximation". In: ETRI Journal 40.4 (Aug. 2018), pp. 421-434. [Link]
Marcella Astrid, Seung-Ik Lee, and Beom-Su Seo. "Rank selection of CP-decomposed convolutional layers with variational Bayesian matrix factorization". In: International Conference on Advanced Communication Technology (ICACT) (PyeongChang, Korea). Feb. 11-14, 2018, pp. 347-350. [Link]
Marcella Astrid and Seung-Ik Lee. "Compression of deep neural networks using CP decomposition and greedy optimization". In: 한국정보과학회 학술발표논문집 (PyeongChang, Korea). Dec. 21-23, 2016, pp. 540-542. [Link]
Carl Shneider, Nilotpal Sinha, Michele Jamrozik, Marcella Astrid, Peyman Rostami, Anis Kacem, Abdelrahman Shabayek, Djamila Aouada. "Compression of Deep Neural Networks for Space Autonomous Systems". In Space Resources Week 2023 (Luxembourg). April 19-21, 2023. [Link]
Marcella Astrid and Kanisius Karyono. “Konversi Timbangan Digital untuk Pengukuran Volume pada Aplikasi Wadah Pintar". In: Ultima Computing: Jurnal Sistem Komputer, 10(2), pp.41-46. [Link]
Marcella Astrid and Kanisius Karyono. “Communication from Smart Storage Container System Using Bluetooth, ZigBee, and XML-RPC ". In: Advanced Science Letters, 22(10), 2016, pp.3037-3042. [Link]
Oka Mahendra, Djohar Syamsi, Ade Ramdan, and Marcella Astrid. “Design and implementation of data storage system using USB flash drive in a microcontroller based data logger”. In: 2015 International Conference on Automation, Cognitive Science, Optics, Micro Electro-Mechanical System, and Information Technology (ICACOMIT), pp. 58-62. IEEE. [Link]
Muhammad Zaigham Zaheer, Marcella Astrid, and Seung-Ik Lee. “A Simple and Efficient Background Separation Method for Stationary Camera Based Videos”. In: 2021 The Institute of Electronics and Information Engineers Summer Conference (IEIE2021) (Jeju, Korea). June 30–July 2, 2021, pp. 1625–1627. [Link]
Hwa-Yeon Kim, Jinsu Lee, Ny Young Yeo, Marcella Astrid, Seung-Ik Lee, and Young-Kil Kim. "CNN based sentence classification with semantic features using word clustering". In: International Conference on ICT Convergence (ICTC) (Jeju, Korea). Oct. 17-19, 2018. [Link]