Allaoui, M. L.; Allili, M. S. LG-TargetSeg: Deep semantic fusion via language-conditioned selective scanning for targeted medical image segmentation Article de journal Dans: Information Fusion, vol. 139, 2027, ISSN: 15662535 (ISSN). @article{allaouiLGTargetSegDeepSemantic2027,
title = {LG-TargetSeg: Deep semantic fusion via language-conditioned selective scanning for targeted medical image segmentation},
author = {M. L. Allaoui and M. S. Allili},
url = {https://www.scopus.com/pages/publications/105051242411?origin=resultslist},
doi = {10.1016/j.inffus.2026.104797},
issn = {15662535 (ISSN)},
year = {2027},
date = {2027-01-01},
journal = {Information Fusion},
volume = {139},
publisher = {Elsevier B.V.},
abstract = {Clinical language defines the semantic intent of targeted medical image segmentation, yet most vision–language methods incorporate it only at a shallow level or through training-time conditioning, leaving spatial reasoning largely language-blind. We propose LG-TargetSeg (Language-Guided Targeted Segmentation), a cross-modal framework that embeds clinical language directly into the selective scan of a Mamba-based encoder-decoder. Natural-language prompts, encoded by a frozen MedSigLIP foundation model, shape selective scanning throughout the encoder–decoder and additionally adapt the bottleneck state transition, alongside gated modulation and cross-attention, enabling semantic guidance to continuously shape feature propagation toward the target anatomy. A Text-Driven Selective Scan 2D (TD-SS2D) module achieves prompt-aware multi-scale fusion with linear complexity in the number of spatial tokens. To improve robustness to boundary ambiguity and class imbalance, we introduce the Reinforced Gaussian Dice Loss (RGDL) with learnable weighting parameters. Evaluated under both task-specific and universal generalization settings, LG-TargetSeg achieves state-of-the-art performance. Moreover, its prompt-driven selectivity remains reliable under genuine multi-target competition: on abdominal CT images containing up to 16 annotated organs, changing only the text prompt on a frozen model produces organ masks with less than 1% pairwise overlap. Additional materials and code are available at: https://github.com/MOHAMEDLamine77/LG-TargetSeg . © 2026 Elsevier B.V.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Clinical language defines the semantic intent of targeted medical image segmentation, yet most vision–language methods incorporate it only at a shallow level or through training-time conditioning, leaving spatial reasoning largely language-blind. We propose LG-TargetSeg (Language-Guided Targeted Segmentation), a cross-modal framework that embeds clinical language directly into the selective scan of a Mamba-based encoder-decoder. Natural-language prompts, encoded by a frozen MedSigLIP foundation model, shape selective scanning throughout the encoder–decoder and additionally adapt the bottleneck state transition, alongside gated modulation and cross-attention, enabling semantic guidance to continuously shape feature propagation toward the target anatomy. A Text-Driven Selective Scan 2D (TD-SS2D) module achieves prompt-aware multi-scale fusion with linear complexity in the number of spatial tokens. To improve robustness to boundary ambiguity and class imbalance, we introduce the Reinforced Gaussian Dice Loss (RGDL) with learnable weighting parameters. Evaluated under both task-specific and universal generalization settings, LG-TargetSeg achieves state-of-the-art performance. Moreover, its prompt-driven selectivity remains reliable under genuine multi-target competition: on abdominal CT images containing up to 16 annotated organs, changing only the text prompt on a frozen model produces organ masks with less than 1% pairwise overlap. Additional materials and code are available at: https://github.com/MOHAMEDLamine77/LG-TargetSeg . © 2026 Elsevier B.V. |
Abdollahzadeh, S.; Allili, M. S.; Boulmerka, A.; Lapointe, J. -F. A Vision-Based Framework for Safe Landing Zone Mapping of UAVs in Dynamic Environments Article de journal Dans: IEEE Open Journal of the Computer Society, vol. 7, p. 492–503, 2026, ISSN: 26441268 (ISSN). @article{abdollahzadeh_vision-based_2026,
title = {A Vision-Based Framework for Safe Landing Zone Mapping of UAVs in Dynamic Environments},
author = {S. Abdollahzadeh and M. S. Allili and A. Boulmerka and J. -F. Lapointe},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105029942397&doi=10.1109%2FOJCS.2026.3663268&partnerID=40&md5=b11484e035458c84b1d3f6780b92c91c},
doi = {10.1109/OJCS.2026.3663268},
issn = {26441268 (ISSN)},
year = {2026},
date = {2026-01-01},
journal = {IEEE Open Journal of the Computer Society},
volume = {7},
pages = {492–503},
abstract = {Identification safe landing zones (SLZ) for Uncrewed Aerial Vehicles (UAVs) is important to ensure reliable and safe navigation, especially when they are operated in complex and safety-critical environments. However, this is a challenging task due to obstacles and UAV motion. This paper proposes a vision-based framework that maps SLZs in dynamic scenes by integrating several functionalities for analyzing visually static and dynamic aspects of a scene. Static analysis is achieved through context-aware segmentation which divides the image into thematic classes enabling to identify suitable landing surfaces (e.g., roads, grass). For dynamic content analysis, we combine object detection, tracking, and trajectory prediction to determine object occupancy and identify regions free of obstacles. Trajectory prediction is performed through a novel encoder–decoder architecture taking past object positions to predict the most likely future locations. To ensure stable and robust trajectory prediction, we introduce an optimized homography computation using multi-scale image analysis and cumulative updates to compensate UAV motion. We tested our framework on different operational scenarios, including urban and natural scenes with moving objects like vehicles and pedestrians. Obtained results demonstrate its strong performance, and its significant potential for enabling autonomous and safe UAV navigation. © 2020 IEEE.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Identification safe landing zones (SLZ) for Uncrewed Aerial Vehicles (UAVs) is important to ensure reliable and safe navigation, especially when they are operated in complex and safety-critical environments. However, this is a challenging task due to obstacles and UAV motion. This paper proposes a vision-based framework that maps SLZs in dynamic scenes by integrating several functionalities for analyzing visually static and dynamic aspects of a scene. Static analysis is achieved through context-aware segmentation which divides the image into thematic classes enabling to identify suitable landing surfaces (e.g., roads, grass). For dynamic content analysis, we combine object detection, tracking, and trajectory prediction to determine object occupancy and identify regions free of obstacles. Trajectory prediction is performed through a novel encoder–decoder architecture taking past object positions to predict the most likely future locations. To ensure stable and robust trajectory prediction, we introduce an optimized homography computation using multi-scale image analysis and cumulative updates to compensate UAV motion. We tested our framework on different operational scenarios, including urban and natural scenes with moving objects like vehicles and pedestrians. Obtained results demonstrate its strong performance, and its significant potential for enabling autonomous and safe UAV navigation. © 2020 IEEE. |
Gapski, M. C. B.; Kawai, V. A. S.; Leticio, G. R.; Valem, L. P.; Pedronette, D. C. G.; Allili, M. S. Graph Neural Networks for Semi-Supervised Image Classification with Multi-Feature Aggregation Article de journal Dans: Journal of the Brazilian Computer Society, vol. 32, no 1, p. 1731–1754, 2026, ISSN: 01046500 (ISSN). @article{gapskiGraphNeuralNetworks2026,
title = {Graph Neural Networks for Semi-Supervised Image Classification with Multi-Feature Aggregation},
author = {M. C. B. Gapski and V. A. S. Kawai and G. R. Leticio and L. P. Valem and D. C. G. Pedronette and M. S. Allili},
url = {https://www.scopus.com/pages/publications/105045179876?origin=resultslist},
doi = {10.5753/jbcs.2026.5880},
issn = {01046500 (ISSN)},
year = {2026},
date = {2026-01-01},
journal = {Journal of the Brazilian Computer Society},
volume = {32},
number = {1},
pages = {1731–1754},
publisher = {Brazilian Computing Society},
abstract = {Feature extraction involves the identification and extraction of salient characteristics or patterns, including edges, textures, shapes, and color attributes. Contemporary feature extractors predominantly leverage deep learning architectures, such as Convolutional Neural Networks (CNNs) and Vision Transformers (VITs). The availability of diverse feature extractors in the literature provides a wide range of feature representations. Features extracted from an image depend on the specific application, the chosen extractor, and its configuration. Therefore, integrating complementary information by combining distinct extractors offers a promising way to enhance performance. Graph Neural Networks (GNNs), particularly Graph Convolutional Networks (GCNs), have emerged as powerful and widely adopted approaches for semi-supervised image classification, as they effectively leverage both labeled and unlabeled data while exploiting the underlying graph structures that capture relationships among samples. This study proposes a novel approach for GNNs in scenarios where labeled data is scarce, by integrating diverse sets of feature and graph representations derived from various extractors in classification scenarios. Experimental investigations were conducted, encompassing combinations of distinct feature and graph extractors, as well as rank aggregation strategies. The primary contributions of this work are underscored by the experimental findings, which demonstrate that the strategic combination of feature and graph representations, coupled with the application of manifold learning for graph processing, leads to significant improvements in classification accuracy across the majority of experimental conditions. Furthermore, the utilization of rank aggregation techniques to integrate features from different extractors was shown to enhance classification accuracy. © 2026, Brazilian Computing Society. All rights reserved.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Feature extraction involves the identification and extraction of salient characteristics or patterns, including edges, textures, shapes, and color attributes. Contemporary feature extractors predominantly leverage deep learning architectures, such as Convolutional Neural Networks (CNNs) and Vision Transformers (VITs). The availability of diverse feature extractors in the literature provides a wide range of feature representations. Features extracted from an image depend on the specific application, the chosen extractor, and its configuration. Therefore, integrating complementary information by combining distinct extractors offers a promising way to enhance performance. Graph Neural Networks (GNNs), particularly Graph Convolutional Networks (GCNs), have emerged as powerful and widely adopted approaches for semi-supervised image classification, as they effectively leverage both labeled and unlabeled data while exploiting the underlying graph structures that capture relationships among samples. This study proposes a novel approach for GNNs in scenarios where labeled data is scarce, by integrating diverse sets of feature and graph representations derived from various extractors in classification scenarios. Experimental investigations were conducted, encompassing combinations of distinct feature and graph extractors, as well as rank aggregation strategies. The primary contributions of this work are underscored by the experimental findings, which demonstrate that the strategic combination of feature and graph representations, coupled with the application of manifold learning for graph processing, leads to significant improvements in classification accuracy across the majority of experimental conditions. Furthermore, the utilization of rank aggregation techniques to integrate features from different extractors was shown to enhance classification accuracy. © 2026, Brazilian Computing Society. All rights reserved. |
