Search Results (449)

Fine-grained image recognition is one of the key tasks in the field of computer vision. However, due to subtle inter-class differences and significant intra-class differences, it still faces severe challenges. Conventional approaches often struggle with background interference and feature degradation. To address these issues, we draw inspiration from the human visual system, which adeptly focuses on discriminative regions, to propose a bio-inspired gradient-aware attention mechanism. Our method explicitly models gradient information to guide the attention, mimicking biological edge sensitivity, thereby enhancing the discrimination between global structures and local details. Experiments on the CUB-200-2011, iNaturalist2018, nabbirds and Stanford Cars datasets demonstrated the superiority of our method, achieving Top-1 accuracy rates of 92.9%, 90.5%, 93.1% and 95.1%, respectively. Full article

This paper presents a new image captioning system which contains facial expression recognition as a way to provide better emotional and contextual comprehension of the captions generated. A combination of affective cues and visual features is made, which enables semantically full and emotionally conscious descriptions. Experiments were carried out on two created datasets, FlickrFace11k and COCOFace15k, with standard benchmarks such as BLEU, METEOR, ROUGE-L, CIDEr, and SPICE to analyze their effectiveness. The suggested model produced better results in all metrics as compared to baselines, like Show-Attend-Tell and Up-Down, remaining consistently better on all the scores. Remarkably, it has reached gains of 2.5 points on CIDEr and 1.0 on SPICE, which means a closer correlation to the prompt captions made by people. A 5-fold cross-validation confirmed the model’s robustness, with minimal standard deviation across folds (<±0.2). Qualitative results further demonstrated its ability to capture fine-grained emotional expressions often missed by conventional models. These findings underscore the model’s potential in affective computing, assistive technologies, and human-centric AI applications. The pipeline is designed for on-prem/edge deployment with lightweight interfaces to IoT middleware (MQTT/OPC UA), enabling smart-factory integration. These characteristics align the method with Industry 4.0 sensor networks and human-centric analytics. Full article

At the intersection of the circular economy and artificial intelligence (AI), high-value secondhand trading faces a “triple decision dilemma” of cognitive overload, trust risk, and emotional attachment. To address the limits of traditional human-centered theories, this study develops and empirically tests a novel framework of Algorithmic Empowerment. Drawing on data from 1396 users of Chinese secondhand luxury platforms and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM), the findings reveal that users’ empowerment perception arises from three dimensions—Algorithmic Connectivity (AC), Human–Agent Symbiotic Trust (HAST), and Algorithmic Value Alignment (AVA). This perceived empowerment affects participation willingness through two parallel pathways: the social pathway, where algorithmic curation shapes social norms and recognition, and the cognitive pathway, where AI enhances decision fluency and reduces cognitive friction. The results confirm the dual mediating effects of these mechanisms. This study advances understanding of human–AI collaboration in sustainable consumption by conceptualizing empowerment as the bridge linking algorithmic functions to user engagement, and provides actionable implications for designing AI systems that both enhance efficiency and foster user trust and identification. Full article

An increasing number of juveniles are accessing adult-oriented venues, such as bars and nightclubs, where supervision is frequently inadequate, thereby elevating their risk of both offline harm and unmonitored exposure to harmful online content. Existing facial age estimation systems, which are primarily designed for adults, have significant limitations when it comes to protecting juveniles, hindering the efficiency of supervising them in key venues. To address these challenges, this study proposes a facial age estimation solution for juvenile protection. First, we have designed a ‘detection–cropping–classification’ framework comprising three stages. This first detects facial regions using a detection algorithm, then crops the image before inputting the results into a classification model for age estimation. Secondly, we constructed the the Juvenile Protection Surveillance and Detection (JPSD) Dataset by integrating five public datasets: UTKface, AgeDB, APPA-REAL, MegaAge and FG-NET. This dataset contains 14,260 images categorised into four age groups: 0–8 years, 8–14 years, 14–18 years and over 18 years. Thirdly, we conducted baseline model comparisons. In the object detection phase, three YOLO algorithms were selected for face recognition. In the age estimation phase, traditional convolutional neural networks (CNNs), such as ResNet50 and VGG16, were contrasted with vision transformer (ViT)-based models, such as ViT and BiFormer. Gradient-weighted Class Activation Mapping (Grad-CAM) was used for visual analysis to highlight differences in the models’ decision-making processes. Experiments revealed that YOLOv11 is the optimal detector for accurate facial localisation, and that ResNet50 is the best base classifier for enhancing age-sensitive feature extraction, outperforming BiFormer. The results show that the framework achieves Recall of 89.17% for the 0–8 age group and 95.17% for the over-18 age group. However, we have found that the current model has low Recall rates for the 8–14 and 14–18 age groups. Therefore, in the near term, we emphasise that this technology should only be used as a decision-support tool under strict human-in-the-loop supervision. This study provides an essential dataset and technical framework for juvenile facial age estimation, offering support for juvenile online protection, smart policing and venue supervision. Full article

Human activity recognition (HAR) based on wearable sensors is a key technology in the fields of smart sensing and health monitoring. With the rapid development of deep learning, its powerful feature extraction capabilities have significantly enhanced recognition performance and reduced reliance on traditional handcrafted feature engineering. However, current deep learning models still face challenges in effectively capturing complex temporal dependencies in long-term time-series sensor data and addressing information redundancy, which affect model recognition accuracy and generalization ability. To address these issues, this paper proposes an innovative CNN-BiGRU–Transformer hybrid deep learning model aimed at improving the accuracy and robustness of human activity recognition. The proposed model integrates a multi-branch Convolutional Neural Network (CNN) to effectively extract multi-scale local spatial features, and combines a Bidirectional Gated Recurrent Unit (BiGRU) with a Transformer hybrid module for modeling temporal dependencies and extracting temporal features in long-term time-series data. Additionally, an attention mechanism is incorporated to dynamically allocate weights, suppress redundant information, and enhance key features, further improving recognition performance. To demonstrate the capability of the proposed model, evaluations are performed on three public datasets: WISDM, PAMAP2, and UCI-HAR. The model achieved recognition accuracies of 98.41%, 95.62%, and 96.74% on the three datasets, respectively, outperforming several state-of-the-art methods. These results confirm that the proposed approach effectively addresses feature extraction and redundancy challenges in long-term sensor time-series data and provides a robust solution for wearable sensor-based human activity recognition. Full article

With the emergence of smart agriculture, precise behavior recognition in tea gardens has become increasingly important for operational monitoring and intelligent management. However, existing behavior detection systems face limitations when deployed in real-world agricultural environments, particularly due to dense vegetation, variable lighting, and diverse human–machine interactions. This paper proposes a novel deep learning framework for picking behavior recognition tailored to complex tea plantation environments. We first construct a large-scale, annotated dataset comprising 12,195 images across 7 behavior categories, collected from both field and web sources, capturing a diverse range of geographic, temporal, and environmental conditions. To address occlusion and multi-scale detection challenges, we enhance YOLOv5 by integrating an Exponential Moving Average (EMA) attention mechanism, Complete Intersection over Union (CIoU) loss, and Atrous Spatial Pyramid Pooling (ASPP), achieving a 73.6% mAP@0.5, representing an 11.6% relative improvement over the baseline model, which indicates a notable enhancement in detection accuracy under complex tea garden conditions. Furthermore, we propose an SE-Faster R-CNN model by embedding Squeeze-and-Excitation (SE) channel attention modules and anchor box optimization strategies, which significantly boosts performance in complex scenarios. A lightweight visual interface for real-time image and video-based detection is also developed to enhance the practical deployability of the system. Experimental results demonstrate the effectiveness, robustness, and real-time potential of the proposed system in recognizing tea garden behaviors under real field conditions. Full article

Sitting posture recognition, defined as automatically localizing and categorizing seated human postures, has become essential for large-scale ergonomics assessment and longitudinal health-risk monitoring in classrooms and offices. However, in real-world multi-person scenes, pervasive occlusions and overlaps induce keypoint misalignment, causing global-attention backbones to fail to localize critical local structures. Moreover, annotation scarcity makes small-sample training commonplace, leaving models insufficiently robust to misalignment perturbations and thereby limiting cross-domain generalization. To address these challenges, we propose LAViTSPose, a lightweight cascaded framework for sitting posture recognition. Concretely, a YOLOR-based detector trained with a Range-aware IoU (RaIoU) loss yields tight person crops under partial visibility; ESBody suppresses cross-person leakage and estimates occlusion/head-orientation cues; a compact ViT head (MLiT) with Spatial Displacement Contact (SDC) and a learnable temperature (LT) mechanism performs skeleton-only classification with a local structural-consistency regularizer. From an information-theoretic perspective, our design enhances discriminative feature compactness and reduces structural entropy under occlusion and annotation scarcity. We conducted a systematic evaluation on the USSP dataset, and the results show that LAViTSPose outperforms existing methods on both sitting posture classification and face-orientation recognition while meeting real-time inference requirements. Full article

Stress, workload, and uncertainty characterize occupational tasks across sports, healthcare, military, and transportation domains. Emerging theory and empirical research suggest that coordinated whole-body movements may reflect these transient mental states. Wearable sensors and optical motion capture offer opportunities to quantify such movement dynamics and classify mental states that influence occupational performance and human–machine interaction. We tested this possibility in a small pilot study (N = 10) designed to test feasibility and identify preliminary movement features linked to mental states. Participants performed a perceptual decision-making task involving facial emotion recognition (i.e., deciding whether depicted faces were happy versus angry) with variable levels of stress (via a risk of electric shock), workload (via time pressure), and uncertainty (via visual degradation of task stimuli). The time series of movement trajectories was analyzed both holistically (full trajectory) and by phase: lowered (early), raising (middle), aiming (late), and face-to-face (sequential). For each epoch, up to 3844 linear and non-linear features were extracted across temporal, spectral, probability, divergence, and fractal domains. Features were entered into a repeated 10-fold cross-validation procedure using 80/20 train/test splits. Feature selection was conducted with the T-Rex Selector, and selected features were used to train a scikit-learn pipeline with a Robust Scaler and a Logistic Regression classifier. Models achieved mean ROC AUC scores as high as 0.76 for stress classification, with the highest sensitivity during the full movement trajectory and middle (raise) phases. Classification of workload and uncertainty states was less successful. These findings demonstrate the potential of movement-based sensing to infer stress states in applied settings and inform future human–machine interface development. Full article

Human Immunodeficiency Virus (HIV) infection is associated with a wide spectrum of urological manifestations, reflecting both the direct effects of viral infection and the indirect consequences of immunosuppression, opportunistic infections, malignancies and long-term combined antiretroviral therapy (cART). This narrative review provides a contemporary, multifaceted overview of the clinical and pathological presentations of urological conditions in people living with HIV (PLWHIV), based on articles published between 1989 and 2025. Conditions discussed include HIV-associated nephropathy (HIVAN), opportunistic genitourinary infections, malignancies such as Kaposi sarcoma and lymphoma, as well as non-infectious complications such as HIV-associated nephropathy and erectile dysfunction (ED). The review highlights the evolving epidemiology of these conditions in the cART era, with a noted decline in opportunistic infections but a rising burden of chronic kidney disease and malignancies, largely due to improved survival and ageing of the HIV-positive population. Pathological insights are explored and discussed, including mechanisms of HIV-associated renal injury, such as direct viral infection of renal epithelial cells and genetic predispositions linked to Apolipoprotein L1 (APOL1) variants. In addition, psychosocial factors, including anxiety, stress, stigma, and alcohol use, are discussed, as they may contribute to late presentation to clinical urology services. The review also considers the challenges faced in low and middle-income countries, the impact of HIV on urological services, and the important role of palliative care in advanced disease. Ultimately, this review underscores the need for early recognition, comprehensive diagnostic and surgical evaluation, and integrated social, psychological, and palliative management strategies tailored to the unique needs of PLWHIV. A deeper understanding of the interplay between HIV, cART, psychosocial determinants, and urological health is essential for improving patient outcomes and guiding future research in this evolving field. Full article

In this study, we present a pilot investigation using a single Purple Heart plant (Tradescantia pallida) to explore whether bioelectrical signals for dual-purpose classification tasks: environmental state detection and human emotion recognition. Using an AD8232 ECG sensor at 400 Hz sampling rate, we recorded 3 s bioelectrical signal segments with 1 s overlap, converting them to mel-spectrograms for ResNet18 CNN (Convolutional Neural Network) classification. For lamp on/off detection, we achieved 85.4% accuracy with balanced precision (0.85–0.86) and recall (0.84–0.86) metrics across 2767 spectrogram samples. For human emotion classification, our system achieved optimal performance at 73% accuracy with 1 s lag, distinguishing between happy and sad emotional states across 1619 samples. These results should be viewed as preliminary and exploratory, demonstrating feasibility rather than definitive evidence of plant-based emotion sensing. Replication across plants, days, and experimental sites will be essential to establish robustness. The current study is limited by a single-plant setup, modest sample size, and reliance on human face-tracking labels, which together preclude strong claims about generalizability. Full article

Emotion recognition based on electroencephalography (EEG) has gained significant attention due to its potential applications in human–computer interaction, affective computing, and mental health assessment. This study presents a convolutional neural network-based approach to emotion valence prediction model development using 4-channel headband EEG data as well as its evaluation based on computer vision emotion valence recognition. We trained a model on the publicly available FACED and SEED datasets and tested it on a newly collected dataset recorded using a wearable BrainBit headband. The model’s performance is evaluated using both standard train–validation–test splitting and a leave-one-subject-out cross-validation strategy. Additionally, the model is evaluated on computer vision-based emotion recognition system to assess the reliability and consistency of EEG-based emotion prediction. Experimental results demonstrate that the CNN model achieves competitive accuracy in predicting emotion valence from EEG signals, despite the challenges posed by limited channel availability and individual variability. The findings show the usability of compact EEG devices for real-time emotion recognition and their potential integration into adaptive user interfaces and mental health applications. Full article

Wireless contactless human activity sensing is a new type of sensing method that uses the propagation characteristics of wireless signals to accurately perceive and understand human behavior. However, facing the huge amount of newly generated data and expanding action categories in the sensing process, the traditional model needs to be retrained frequently. This model not only brings significant computational power overhead, but also seriously affects the real-time response speed of the system. To address this problem, this paper proposes a model, WIS (Wireless Incremental Sense), which is composed of two parts. The first part is the basic sensing module NFFCN (Nearest Neighbor Feature Fusion Classification). NFFCN is a fusion classification method based on Nearest Class Mean (NCM) classifier and Random Forest (RF). By combining the local feature extraction ability of NCM and the integrated learning advantage of RF, this method can efficiently extract human behavior features from wireless signals and achieve high-precision classification. The second part is the incremental learning module NFFCN-RTST, which uses the retraining subtree (RTST) incremental strategy to optimize the model. Unlike update leaf statistics (ULS) and the Incrementally Grow Tree (IGT) incremental strategy, RTST not only updates the statistical data of leaf nodes but also dynamically adjusts the previously learned splitting function, so as to better adapt to new data and categories. In the experimental validation on the rRuler and Stan WiFi datasets, the average recognition accuracy of NFFCN reaches 87.1% and 98.4%, respectively. In the class-incremental experimental validation, the recognition accuracy of WIS reaches 87% and 95%, respectively. Full article

As many face significant financial costs and legal barriers to accessing justice to remedy systemic human rights violations rooted in colonialism, they are increasingly turning to class action litigation for recognition of harms and to safeguard others. Drawing on Canadian examples, including a class action involving First Nations children, this article examines the complex and sometimes conflicting relationship between class actions and human rights remedies. The paper highlights the risks of class actions displacing human rights awards, the ethical challenges in relationships between class counsel and Indigenous victims, and the limited effectiveness of settlements in preventing recurring injustices. The article concludes by calling for stronger regulation of class action lawyers and tethering such proceedings to the United Nations Declaration on the Rights of Indigenous Peoples and other human rights standards, including the United Nations Convention on the Rights of the Child. Full article

With the rapid advancement of aviation technology, modern aircraft cockpits are evolving toward high automation and intelligence, making pilot-cockpit interaction a critical factor influencing flight safety and efficiency. Pilot pose estimation and behavior recognition are critical for monitoring pilot state, preventing operational errors, and enabling adaptive human–machine interaction, thus playing an essential role in aviation safety assurance and intelligent cockpit development. However, existing methods face challenges in real-time performance, reliability, and computational complexity in practical applications. Traditional approaches, such as wearable sensors and image-processing-based algorithms, demonstrate certain effectiveness but still exhibit limitations in aviation environments. To address these issues, this paper proposes a lightweight pilot pose estimation and behavior recognition framework, integrating Vision Transformer with depth-wise separable convolution to optimize the accuracy and efficiency of keypoint detection. Additionally, a novel multimodal data fusion technique is introduced, along with a scientifically designed evaluation system, to enhance the robustness and security of the system in complex environments. Experimental results on a pilot keypoint detection dataset captured in a simulated cockpit environment show that the proposed method achieves 81.9 AP, while substantially reducing model parameters and notably improving inference efficiency compared with HRNet. This study provides new insights and methodologies for the design and evaluation of aviation human-machine interaction systems. Full article

Learning from Demonstration (LfD) enables robots to acquire manipulation skills by observing human actions. However, existing methods often face challenges such as high computational cost, limited generalizability, and a loss of key interaction details. This study presents a compact representation for interaction recognition in LfD that encodes human–object interactions using 2D wrist trajectories and 3D object poses. A lightweight extraction pipeline combines MediaPipe-based wrist tracking with FoundationPose-based 6-DoF object estimation to obtain these trajectories directly from RGB-D video without specialized sensors or heavy preprocessing. Experiments on the GRAB and FPHA datasets show that the representation effectively captures task-relevant interactions, achieving 94.6% accuracy on GRAB and 96.0% on FPHA with well-calibrated probability predictions. Both Bidirectional Long Short-Term Memory (Bi-LSTM) with attention and Transformer architectures deliver consistent performance, confirming robustness and generalizability. The method achieves sub-second inference, a memory footprint under 1 GB, and reliable operation on both GPU and CPU platforms, enabling deployment on edge devices such as NVIDIA Jetson. By bridging pose-based and object-centric paradigms, this approach offers a compact and efficient foundation for scalable robot learning while preserving essential spatiotemporal dynamics. Full article