publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
2026
- Out of Context: Reliability in Multimodal Anomaly Detection Requires Contextual InferencearXiv preprint arXiv:2604.13252, 2026
- A Hyperbolic Perspective on Hierarchical Structure in Object-Centric Scene RepresentationsarXiv preprint arXiv:2603.14022, 2026
2025
- Meta-Token Learning for Thermal Object Detection with TransformersIn 2025 IEEE 1st International Conference on Application of Information Technologies in Engineering, Management and Science (ICAI-TEMS), 2025
- SlotMatch: Distilling Object-Centric Representations for Unsupervised Video SegmentationarXiv preprint arXiv:2508.03411, 2025
2024
- arXivFoundation Models for Video Understanding: A SurveyarXiv preprint arXiv:2405.03770, 2024
- WACVCL-MAE: Curriculum-Learned Masked AutoencodersIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024
2023
- TPAMISelf-supervised masked convolutional transformer block for anomaly detectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- WACVThermalsynth: A novel approach for generating synthetic thermal human scenariosIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023
2022
- CVPRSelf-supervised predictive convolutional attentive block for anomaly detectionIn Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022
- Appl. Sci.New Metric for Evaluation of Deep Neural Network Applied in Vision-Based SystemsApplied Sciences, 2022
- IntelliSysAttention-enabled object detection to improve one-stage trackerIn Intelligent Systems and Applications: Proceedings of the 2021 Intelligent Systems Conference (IntelliSys) Volume 2, 2022
2021
- ICCVTemporal cues from socially unacceptable trajectories for anomaly detectionIn Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021
2018
- FEVERInformation nutrition labels: A plugin for online news evaluationIn Proceedings of the first workshop on fact extraction and verification (FEVER), 2018