Informatica

Video anomaly detection is a critical component of intelligent surveillance systems, where detection accuracy, temporal stability, computational efficiency, and real-world deployment feasibility must be jointly considered. Existing studies frequently rely on ROC–AUC as the primary evaluation metric, providing limited insight into practical system performance. This study prese...

Large language models (LLMs) have demonstrated exceptional capabilities across multiple domains and emerged as the core driving force in natural language processing. Their reasoning however can be associated with logical flaws and lack of stability when attempting to solve difficult problems that require multi-step deduction, cross-domain knowledge or implicit constraints, wi...

Power line communication and installation in renewable energy–based off-grid and microgrid systems are highly sensitive to electrical disturbances, environmental variability, and appliance-induced non-stationary noise. This paper proposes an RBF neural network–based multi-feature disturbance analysis framework for power line installation assessment. The model integrates power...

Cross-view gait recognition remains vulnerable to viewpoint shifts and appearance changes, especially
under carrying and clothing covariates. We propose BFS-CNN-ECA-GMP-GRU-MSP, an enhanced version
of our previous BFS-CNN-GMP-GRU-MSP framework, by introducing two upgrades: multi-stage
lightweight channel recalibration with Efficient Channel Attention (ECA) and cosine...

Vision-Language Models (VLMs) exhibit excellent zero-shot and few-shot capabilities in downstream tasks by maximizing the similarity between matched image-text pairs. However, the dual-encoder structure of VLMs introduces a large number of parameters, which limits their practical deployment. Knowledge distillation transfers the knowledge of VLMs to lightweight student models ...