2661 papers
This paper proposes TMB-CMSBT, a novel framework integrating blockchain technology and ensemble learning to enhance secure VM management, user authentication, and real-time threat detection in cloud environments while addressing the limitations of traditional centralized systems.
This paper proposes TriFuseDroid, a robust Android malware detection scheme that analyzes the impact of code obfuscation on static features and employs a multi-feature fusion network to convert resilient static views into image representations, achieving high accuracy and generalization against diverse obfuscation techniques without requiring obfuscated training samples.
This study demonstrates that ten diverse deep learning models, including CNNs and Vision Transformers utilizing a multi-view attention mechanism, achieve high diagnostic accuracy and rapid processing speeds for knee fractures on X-rays, suggesting their strong potential as clinical decision support tools even in resource-limited settings.
This study presents a web-based decision support system that integrates class and thesis/capstone defense scheduling through a constraint-aware, rule-based workflow, demonstrating high user satisfaction and operational efficiency in deployments across two higher education institutions.
This paper proposes a robust multimodal deep learning framework that fuses CNN-based visual crack detection with LSTM-processed sensor time-series data to overcome the generalization limitations of single-modality approaches, achieving 94% overall accuracy and enhanced recall for sustainable bridge health monitoring in smart cities.
This paper presents "Ctrl+You," a cloud-backed, adaptive accessibility interface that unifies assistive tools across web, desktop, and mobile platforms via a single user profile, demonstrating through a two-week field evaluation at Mumbai's UMED Disability Centre that this approach significantly reduces data entry errors and caretaker intervention for individuals with diverse disabilities.
This paper proposes a zero-shot low-light image enhancement framework that leverages a pretrained diffusion model as a prior and refines its predictions via Hamiltonian Monte Carlo sampling under Fourier phase constraints to effectively suppress noise, preserve structural details, and ensure measurement consistency without additional training.
This paper proposes a Privileged Knowledge Distillation framework (PKD-ISLR) that improves isolated sign language recognition in low-resolution videos by transferring discriminative knowledge from a multimodal high-resolution teacher model to a low-resolution student, outperforming existing baselines on WLASL and ASLCitizen benchmarks.
This paper proposes MDRC, a mechanism-decoupled retrieval-guided conditional recovery framework that addresses incomplete multimodal emotion recognition by modeling shared-private semantics and leveraging retrieval evidence through controlled prior guidance and bounded residual refinement to enhance robustness against missing modalities.
This paper proposes SATrans, a novel attention-based temporal framework that leverages multimodal physiological signals and dynamic PAD-driven labeling to achieve highly accurate, robust, and scalable real-time classification of depression severity across various time resolutions.