https://www.um.edu.mt/library/oar/handle/123456789/8369 2026-10-29T05:48:31Z 2026-10-29T05:48:31Z Hossain, Zobaer So, Averie Ho Zoen Silwal, Silviya Gongora, H. Andres Gonzalez Samin, Ahnaf Mozib Junaed, Jahedul Alam Mazumder, Aritra Saha, Sourav Soha, Sabiha Tahsin https://www.um.edu.mt/library/oar/handle/123456789/150260 2026-10-20T11:33:13Z 2023-07-01T00:00:00Z

Title: garNER at SemEval-2023 : simplified knowledge augmentation for multilingual complex named entity recognition Authors: Hossain, Zobaer; So, Averie Ho Zoen; Silwal, Silviya; Gongora, H. Andres Gonzalez; Samin, Ahnaf Mozib; Junaed, Jahedul Alam; Mazumder, Aritra; Saha, Sourav; Soha, Sabiha Tahsin Abstract: This paper presents our solution, garNER, to the SemEval-2023 MultiConer task. We propose a knowledge augmentation approach by directly querying entities from the Wikipedia API and appending the summaries of the entities to the input sentence. These entities are either retrieved from the labeled training set (Gold Entity) or from off-the-shelf entity taggers (Entity Extractor). Ensemble methods are then applied across multiple models to get the final prediction. Our analysis shows that the added contexts are beneficial only when such contexts are relevant to the target-named entities, but detrimental when the contexts are irrelevant.

2023-07-01T00:00:00Z Grech, Alan Pisani, Daniel Grima, Andre Debono, Carl James Formosa, Saviour Seychell, Dylan https://www.um.edu.mt/library/oar/handle/123456789/149091 2026-09-14T11:18:14Z 2026-01-01T00:00:00Z

Title: Iterative hybrid discrete-continuous viewpoint planning for UAV photogrammetry Authors: Grech, Alan; Pisani, Daniel; Grima, Andre; Debono, Carl James; Formosa, Saviour; Seychell, Dylan Abstract: Unmanned aerial vehicle (UAV) photogrammetry requires camera networks that provide sufficient surface coverage, image overlap, parallax, and resolution, yet conventional flight patterns are often poorly adapted to scene geometry, resulting in local reconstruction errors. This paper proposes an iterative hybrid discrete-continuous viewpoint planning method for targeted UAV photogrammetry from a proxy reconstruction. The method scores sampled surface points using photogrammetric heuristics based on frontality, imaging distance, parallax, and multi-view observation count, while also evaluating the full viewpoint set in terms of visibility, pairwise overlap, and graph connectivity. Candidate viewpoints are generated around weakly observed regions, refined using clustered Covariance Matrix Adaptation Evolution Strategy (CMA-ES) optimisation, and removed when redundant. The final flight path combines close-range detail viewpoints with wider model-coverage viewpoints, balancing local reconstruction quality with global image-network robustness. Evaluation on three synthetic scenes shows that the proposed method improves both reconstruction accuracy and completeness compared with prior UAV path-planning methods.

2026-01-01T00:00:00Z Bartolo, Matthias Seychell, Dylan Hili, Gabriel Montebello, Matthew Debono, Carl James Formosa, Saviour Makantasis, Konstantinos https://www.um.edu.mt/library/oar/handle/123456789/149083 2026-09-14T11:02:47Z 2026-01-01T00:00:00Z

Title: Enhancing object detection with privileged information : a model-agnostic teacher-student approach Authors: Bartolo, Matthias; Seychell, Dylan; Hili, Gabriel; Montebello, Matthew; Debono, Carl James; Formosa, Saviour; Makantasis, Konstantinos Abstract: This paper investigates the integration of the Learning Using Privileged Information (LUPI) paradigm in object detection to exploit fine-grained, descriptive information available during training but not at inference. We introduce a general, model-agnostic methodology for injecting privileged information-such as bounding box masks, saliency maps, and depth cues-into deep learning-based object detectors through a teacher-student architecture. Experiments are conducted across five state-of-the-art object detection models and multiple public benchmarks, including UAV-based litter detection datasets and Pascal VOC 2012, to assess the impact on accuracy, generalization, and computational efficiency. Our results demonstrate that LUPI-trained students consistently outperform their baseline counterparts, achieving significant boosts in detection accuracy with no increase in inference complexity or model size. Performance improvements are especially marked for medium and large objects, while ablation studies reveal that intermediate weighting of teacher guidance optimally balances learning from privileged and standard inputs. The findings affirm that the LUPI framework provides an effective and practical strategy for advancing object detection systems in both resource-constrained and real-world settings.

2026-01-01T00:00:00Z Rašajski, Nemanja Makantasis, Konstantinos Liapis, Antonios Yannakakis, Georgios https://www.um.edu.mt/library/oar/handle/123456789/148974 2026-09-09T09:25:06Z 2026-01-01T00:00:00Z

Title: InvPatch : prefix-based conditional generation for inverse dynamics Authors: Rašajski, Nemanja; Makantasis, Konstantinos; Liapis, Antonios; Yannakakis, Georgios Abstract: Inverse Dynamics Models (IDMs) attempt to predict the actions that cause observable changes in a scene. Current methods for building accurate IDMs either rely on rule-based systems that exploit video metadata or require large-scale training over thousands of video hours. These approaches are inevitably limited to a single domain due to the difficulty of acquiring metadata or sufficient training data across different domains. In response to these challenges, this study draws inspiration from data-efficient video captioning methods, specifically prefix-based conditional generation. This approach maps visual features into prefix tokens that condition the action-prediction process. We introduce InvPatch, a framework that builds on prefix-based conditional generation and extends it by adding learned visual-representation compression. In InvPatch, attention-based patch selection and pooling are applied to features extracted from a ViT backbone, reducing the conditioning input from a set of frame-by-frame features to a single vector. We evaluate our framework across two diverse settings: 3D third-person real world (KIT Bimanual Actions) and 2D synthetic (MUGEN). Our method achieves 97.21% accuracy on MUGEN and surpasses state-of-the-art results on KIT Bimanual Actions. Our sensitivity analysis highlights the data efficiency of this approach, as InvPatch maintains comparable performance even when trained with 30% less data. Additionally, our runtime analysis demonstrates the computational efficiency of InvPatch, which requires fewer trainable parameters and performs fewer FLOPs compared to other methods.

2026-01-01T00:00:00Z