Explore the vast range of titles available.

Ensuring proper Personal Protective Equipment (PPE) compliance is crucial for maintaining worker safety and reducing accident risks on construction sites. Previous research has explored various object detection methodologies for automated monitoring of non-PPE compliance; however, achieving higher accuracy and computational efficiency remains critical for practical real-time applications. Addressing this challenge, the current study presents an extensive evaluation of You Only Look Once version 10 (YOLOv10)-based object detection models designed specifically to detect essential PPE items such as helmets, masks, vests, gloves, and shoes. The analysis utilized an extensive dataset gathered from multiple sources, including surveillance cameras, body-worn camera footage, and publicly accessible benchmark datasets, ensuring thorough and realistic evaluation conditions. The analysis was conducted using an extensive dataset compiled from multiple sources, including surveillance cameras, body-worn camera footage, and publicly available benchmark datasets, to ensure a thorough evaluation under realistic conditions. Experimental outcomes revealed that the Swin Transformer-based YOLOv10 model delivered the best overall performance, achieving AP50 scores of 92.4% for non-helmet, 88.17% for non-mask, 87.17% for non-vest, 85.36% for non-glove, and 83.48% for non-shoes, with an overall average AP50 of 87.32%. Additionally, these findings underscored the superior performance of transformer-based architectures compared to traditional detection methods across multiple backbone configurations. The paper concludes by discussing the practical implications, potential limitations, and broader applicability of the YOLOv10-based approach, while also highlighting opportunities and directions for future advancements.

This paper introduces the GCN-Transformer model, an innovative approach that combines Graph Convolutional Networks (GCNs) and Transformer architectures to enhance spatiotemporal sequence prediction. Targeted at applications requiring precise analysis of complex spatial and temporal data, the model was tested on two distinct datasets: PeMSD8 for traffic flow and KnowAir for air quality monitoring. The GCN-Transformer demonstrated superior performance over traditional models such as LSTMs, standalone GCNs, and other GCN-hybrid models, evidenced by its lower Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). An ablation study confirmed the importance of each component within the model, showing that removing elements like GCN layers, Transformer layers, attention mechanisms, or positional encoding detrimentally impacts performance. Overall, the GCN-Transformer model offers significant theoretical and practical contributions to the field of spatiotemporal data analysis, with potential applications across traffic management, environmental monitoring, and beyond.

Amongst energy-related CO2 emissions, electricity is the largest single contributor, and with the proliferation of electric vehicles and other developments, energy use is expected to increase. Load forecasting is essential for combating these issues as it balances demand and production and contributes to energy management. Current state-of-the-art solutions such as recurrent neural networks (RNNs) and sequence-to-sequence algorithms (Seq2Seq) are highly accurate, but most studies examine them on a single data stream. On the other hand, in natural language processing (NLP), transformer architecture has become the dominant technique, outperforming RNN and Seq2Seq algorithms while also allowing parallelization. Consequently, this paper proposes a transformer-based architecture for load forecasting by modifying the NLP transformer workflow, adding N-space transformation, and designing a novel technique for handling contextual features. Moreover, in contrast to most load forecasting studies, we evaluate the proposed solution on different data streams under various forecasting horizons and input window lengths in order to ensure result reproducibility. Results show that the proposed approach successfully handles time series with contextual data and outperforms the state-of-the-art Seq2Seq models.

Due to its capacity to gather vast, high-level data about human activity from wearable or stationary sensors, human activity recognition substantially impacts people’s day-to-day lives. Multiple people and things may be seen acting in the video, dispersed throughout the frame in various places. Because of this, modeling the interactions between many entities in spatial dimensions is necessary for visual reasoning in the action recognition task. The main aim of this paper is to evaluate and map the current scenario of human actions in red, green, and blue videos, based on deep learning models. A residual network (ResNet) and a vision transformer architecture (ViT) with a semi-supervised learning approach are evaluated. The DINO (self-DIstillation with NO labels) is used to enhance the potential of the ResNet and ViT. The evaluated benchmark is the human motion database (HMDB51), which tries to better capture the richness and complexity of human actions. The obtained results for video classification with the proposed ViT are promising based on performance metrics and results from the recent literature. The results obtained using a bi-dimensional ViT with long short-term memory demonstrated great performance in human action recognition when applied to the HMDB51 dataset. The mentioned architecture presented 96.7 ± 0.35% and 41.0 ± 0.27% in terms of accuracy (mean ± standard deviation values) in the train and test phases of the HMDB51 dataset, respectively.

The rapid spread of misinformation on social platforms has intensified research on automated detection, with Transformer-based architectures becoming a primary technical foundation. However, the volume and diversity of publications make it difficult to track the field’s evolution. It is also challenging to identify the contributors, influential studies, and remaining gaps that shape its knowledge base. This study presents a bibliometric mapping of Transformer-based research on misinformation detection, based on Scopus records retrieved on 3rd March 2026 (n = 3,637). Performance indicators and science mapping analysis are used to profile publication growth, subject-area distribution, leading countries, institutions, and authors, citation impact, and thematic structure. Results show that conference proceedings (47.18%) and journals (41.93%) dominate dissemination, reflecting both rapid-cycle publishing and archival consolidation. Computer Science accounts for most publications (84.99%), while Social Sciences and Medicine contribute non-trivial shares, indicating applied and societal engagement. China, the United States, and India lead in national output, and institutional productivity is concentrated in a small set of research hubs. Citation indicators (h-index = 82; g-index = 154) suggest a broad influence with a distinct, highly cited core. Keyword mapping confirms a stable emphasis on NLP-driven detection in social media and shows recent growth in multimodal approaches and generative-AI-related topics. The findings provide an evidence-based overview of current trends and emerging directions, helping researchers position future work and prioritize underexplored problems.

This paper presents a deep learning-based framework for tactical analysis in football, focusing on modeling structured tracking data rather than attempting full end-to-end perception. We introduce two modular components: Tactiformer, a transformer-based encoder that captures spatiotemporal player dynamics with role- and zone-aware attention, and StratGaze, a segment-level reasoning module that identifies recurring tactical motifs using contrastive sequence modeling. Tactiformer learns representations of coordinated multi-agent behavior at the player level, while StratGaze operates at the segment level to extract interpretable tactical abstractions over time. Our framework is fully data-driven, modular, and compatible with standard football analytics pipelines. We evaluate the approach on benchmark datasets including SoccerNet and PASS, demonstrating consistent improvements in event prediction accuracy, trajectory forecasting, and motif clustering quality over existing baselines. In addition to quantitative results, we provide qualitative visualizations of model attention maps and inferred tactical timelines, supporting the interpretability and usability of the system in real-world scenarios. Rather than solving the entire pipeline from detection to tactical inference, this work targets the reasoning layer and shows how structured spatiotemporal representations, combined with inductive priors, can support scalable, interpretable, and data-efficient football analytics tools suitable for analysts and coaching staff.

This survey provides an in-depth review of large language models (LLMs), highlighting the significant paradigm shift they represent in artificial intelligence. Our purpose is to consolidate state-of-the-art advances in LLM design, training, adaptation, evaluation, and application for both researchers and practitioners. To accomplish this, we trace the evolution of language models and describe core approaches, including parameter-efficient fine-tuning (PEFT). The methodology involves a thorough survey of real-world LLM applications across the scientific, engineering, healthcare, and creative sectors, coupled with a review of current benchmarks. Our findings indicate that high training and inference costs are shaping market structures, raising economic and labor concerns, while also underscoring a persistent need for human oversight in assessment. Key trends include the development of unified multimodal architectures capable of processing varied data inputs and the emergence of agentic systems that exhibit complex behaviors such as tool use and planning. We identify critical open problems, such as detectability, data contamination, generalization, and benchmark diversity. Ultimately, we conclude that overcoming these complex technical, economic, and social challenges necessitates collaborative advancements in adaptation, evaluation, infrastructure, and governance.

The integration of self-attention mechanisms into Spiking Neural Networks (SNNs) has garnered considerable interest in the realm of advanced deep learning, primarily due to their biological properties. Recent advancements in SNN architecture, such as Spikformer, have demonstrated promising outcomes. However, we observe that Spikformer may exhibit excessive energy consumption, potentially attributable to redundant channels and blocks. To mitigate this issue, we propose a one-shot Spiking Transformer Architecture Search method, namely Auto-Spikformer. Auto-Spikformer extends the search space to include both transformer architecture and SNN inner parameters. We train and search the supernet based on weight entanglement, evolutionary search, and the proposed Discrete Spiking Parameters Search (DSPS) methods. Benefiting from these methods, the performance of subnets with weights inherited from the supernet without even retraining is comparable to the original Spikformer. Moreover, we propose a new fitness function aiming to find a Pareto optimal combination balancing energy consumption and accuracy. Our experimental results demonstrate the effectiveness of Auto-Spikformer, which outperforms the original Spikformer and most CNN or ViT models with even fewer parameters and lower energy consumption.

Creating a summarized version of a text document that still conveys precise meaning is an incredibly complex endeavor in natural language processing (NLP). Abstract text summarization (ATS) is the process of using facts from source sentences and merging them into concise representations while maintaining the content and intent of the text. Manually summarizing large amounts of text are challenging and time-consuming for humans. Therefore, text summarization has become an exciting research focus in NLP. This research paper proposed an ATS model using a Transformer Technique with Self-Attention Mechanism (T2SAM) . The self-attention mechanism is added to the transformer to solve the problem of coreference in text. This makes the system to understand the text better. The proposed T2SAM model improves the performance of text summarization. It is trained on the Inshorts News dataset combined with the DUC-2004 shared tasks dataset. The performance of the proposed model has been evaluated using the ROUGE metrics, and it has been shown to outperform the existing state-of-the-art baseline models. The proposed model gives the training loss minimum to 1.8220 from 10.3058 (at the starting point) up to 30 epochs, and it achieved model accuracy 48.50% F1-Score on both the Inshorts and DUC-2004 news datasets.

Vision Transformers have demonstrated strong performance across diverse visual tasks; however, their high computational cost due to long token sequences remains a critical challenge. Sequence reduction via pooling is a common strategy, yet relying on a single pooling operation often limits contextual representation. Motivated by the strong context abstraction capability of pyramid pooling, this work investigates its effective integration within a transformer-based framework for landslide detection from remote sensing imagery. Rather than introducing an entirely new backbone, we build upon the existing Pyramid Pooling Transformer and adapt it for landslide analysis by incorporating a multilayer pyramid pooling–based multi-head self-attention mechanism, enabling efficient sequence reduction while preserving multi-scale contextual information. This task-oriented adaptation allows the model to better capture the spatial heterogeneity and scale variability inherent in landslide scenes. Extensive experiments on a benchmark remote sensing landslide dataset demonstrate that the proposed PPT-based model significantly outperforms conventional CNNs and standard transformer baselines. Compared to state-of-the-art deep learning models, the proposed approach achieves improvements of 7.3% in F1-score and 2% in overall accuracy, highlighting the effectiveness of pyramid pooling–driven attention mechanisms for landslide detection.