ABSTRACT Detecting student behaviour objects in classroom environments is crucial for assessing educational progress, optimizing teaching strategies and improving student learning outcomes. With the ongoing advancement of educational informatization, analysing classroom behaviour has become an important tool for enhancing teaching quality and personalized learning. However, current student behaviour object detection models based on CNN and Transformer architectures face challenges such as large parameter sizes and high inference delays when deployed on edge devices in classrooms, limiting their practical application. To address these issues, this study proposes a lightweight student behaviour detection framework based on the Mamba architecture, aimed at balancing computational efficiency and detection accuracy. First, the framework based on the state‐space model (SSM) efficiently captures global dependencies, using local convolutions to enhance detection accuracy and scene understanding while maintaining real‐time performance. Second, the C2CGA module increases attention diversity through feature splitting, self‐attention, cascading and projected concatenation, deepening the network while reducing computational overhead. Finally, the A2CMoCA module aggregates multi‐scale features, improving the learning of small objects and occluded behaviours. Experiments on a self‐built classroom behaviour dataset (containing eight typical teaching behaviours) show that the proposed method achieves 91.5% detection accuracy while maintaining a lightweight design. Compared to the baseline model, its computational efficiency (5.9G FLOPs) is reduced by 56.6%, the parameter size is compressed to 3.65 M (a 39% reduction) and the inference speed is 3.2 ms, meeting the real‐time monitoring requirements in classroom teaching scenarios.

Low-Light Image Enhancement (LLIE) methods based on either Retinex theory or deep learning still exhibit significant shortcomings in handling image corruptions, such as noise, artifacts, and color distortion. The primary issue is that both Retinex algorithms and existing networks may introduce or amplify these corruptions during enhancement. To address these limitations, we propose the Denoised-Modulated Hybrid-Semantic Scale-Aware Network (DHSNet), a novel one-stage LLIE method. DHSNet integrates a Signal-to-Noise Ratio (SNR)-based denoising mechanism and a Hybrid-Semantic Scale-Aware Module (HSM) to preprocess noise and fuse multi-scale features for robust image enhancement. Moreover, we introduce the Illumination Partial Attention Block (IPAB) to further improve illumination correction and nonlinear transformation capabilities. DHSNet effectively mitigates noise, preserves intricate details, and restores degraded structures. Extensive experiments on multiple LLIE datasets demonstrate that it outperforms state-of-the-art (SOTA) methods in both qualitative and quantitative metrics. Furthermore, DHSNet exhibits strong generalization in no-reference LLIE and low-light object detection tasks, underscoring its practical value for real-world applications.

Complicated background and small object issues are the primary challenges currently confronting remote sensing object detection (RSOD). To tackle the aforementioned issues in RSOD, we propose an axis-squeeze and multirouting scale-adaptive fusion network (AMSFNet). In this network, a unidirectional multiscale coupling module (UMCM) is designed to enhance the object feature extraction capabilities and improve the accuracy of small object detection. Furthermore, utilizing the axis-squeeze and detail enhancement approach, we construct a squeeze-enhanced axial attention module that specifically targets background disruption, which can efficiently aggregate global and local information and reduce the impact of intricate background noise on the object. To improve the synergy between features of varying sizes and ensure that the model can allow for a compromise between detecting small and large targets simultaneously, a multirouting SAF approach is proposed, which combines fine-grained features with high-level features using multiple feed-forward connections. The proposed approach has been shown to be efficient by ablation and comparison experiments performed on three public benchmark datasets: RSOD, VisDrone, and DIOR. AMSFNet achieves a mean average precision (mAP) of 95.4%, 88.7%, and 36.6% on the RSOD, DIOR, and VisDrone datasets, respectively.

To fully leverage contextual information for the precise segmentation of objects in remote sensing images, while addressing the challenges associated with substantial object scale variations and complex backgrounds, we propose a lightweight cross-domain coupling network (LCCN) tailored for semantic segmentation of high-resolution remote sensing images (HRSIs). To standardize feature selection and fusion procedures, the LCCN incorporates an innovative Encoder-Coupler-Decoder architecture designed to facilitate key feature extraction and optimization. A cross-domain coupling module (CDCM) is created in the Coupler to conduct preliminary features screening of spaces and dimensions based on channel and spatial attention. It performs multi-scale feature extraction and global information modeling through the feature grouping and loop aggregation. This helps to extract key features while reducing the computational overhead. To further decrease the interference from complex backgrounds, a secondary optimization of the key features is carried out: a lightweight fully-featured mapping attention module (LFMAM) is designed within the Decoder. LFMAM utilizes an interactive fusion strategy and a lightweight linear self-attention mechanism, comprehensively considering all interactions between global-to-global, global-to-local, local-to-local, and local-to-global processes. By capturing the effective correlations and variances among features to further refine them, it enables the network to further optimize the crucial information while ensuring light weight. We have conducted extensive comparison experiments and ablation experiments on the ISPRS Vaihingen and ISPRS Potsdam datasets. The extensive experimental results demonstrate that our proposed LCCN can obtain superior performance compared to other advanced semantic segmentation models.

Prevalent nighttime person re-identification (ReID) methods typically combine image relighting and ReID networks in a sequential manner. However, their performance (recognition accuracy) is limited by the quality of relighting images and insufficient collaboration between image relighting and ReID tasks. To handle these problems, we propose a novel Collaborative Enhancement Network called CENet, which performs the multilevel feature interactions in a parallel framework, for nighttime person ReID. In particular, the designed parallel structure of CENet can not only avoid the impact of the quality of relighting images on ReID performance, but also allow us to mine the collaborative relations between image relighting and person ReID tasks. To this end, we integrate the multilevel feature interactions in CENet, where we first share the Transformer encoder to build the low-level feature interaction, and then perform the feature distillation that transfers the high-level features from image relighting to ReID, thereby alleviating the severe image degradation issue caused by the nighttime scenario while avoiding the impact of relighting images. In addition, the sizes of existing real-world nighttime person ReID datasets are limited, and large-scale synthetic ones exhibit substantial domain gaps with real-world data. To leverage both small-scale real-world and large-scale synthetic training data, we develop a multi-domain learning algorithm, which alternately utilizes both kinds of data to reduce the inter-domain difference in training procedure. Extensive experiments on two real nighttime datasets,Night600andRGBNT201rgb, and a synthetic nighttime ReID dataset are conducted to validate the effectiveness of CENet. We release the code and synthetic dataset at: https://github.com/Alexadlu/CENet.

Graph Convolutional Networks (GCNs) are widely used for skeleton-based action recognition and achieved remarkable performance. Due to the locality of graph convolution, GCNs can only utilize short-range node dependencies but fail to model long-range node relationships. In addition, existing graph convolution based methods normally use a uniform skeleton topology for all frames, which limits the ability of feature learning. To address these issues, we present the Graph Convolution Network with Self-Attention (SelfGCN), which consists of a mixing features across self-attention and graph convolution (MFSG) module and a temporal-specific spatial self-attention (TSSA) module. The MFSG module models local and global relationships between joints by executing graph convolution and self-attention branches in parallel. Its bi-directional interactive learning strategy utilizes complementary clues in the channel dimensions and the spatial dimensions across both of these branches. The TSSA module uses self-attention to learn the spatial relationships between joints of each frame in a skeleton sequence. It also models the unique spatial features of the single frames. We conduct extensive experiments on three popular benchmark datasets, NTU RGB+D, NTU RGB+D120, and Northwestern-UCLA. The results of the experiment demonstrate that our method achieves or exceeds the record accuracies on all three benchmarks. Our project website is available at https://github.com/SunPengP/SelfGCN.

Both point cloud-based and view-based deep learning methods for 3D shape recognition have achieved relatively remarkable results in recent years. However, there are few methods to jointly represent 3D shapes from both point cloud and multi-view modal data. Therefore, we propose a guidance enhancement network (GENet) for 3D shape recognition based on multimodal data. On the one hand, the point cloud is encoded with features from both explicit and implicit aspects, and on the other hand, all views are encoded and constructed as a graph. In the multilayer guidance enhancement module, graph convolutional neural network (GCN) enhances each view feature, and then temporary high-level features (initially point cloud global feature) guide multiple low-level view features to obtain correlation coefficients, through which the views with higher importance are filtered as inputs for the next layer of the structure and the view features in the current layer are weighted and aggregated. The aggregated view features are then connected to the high-level features with residuals to form the enhanced high-level features. The 3D shape descriptor is finally obtained after several guidance and enhancements. The proposed GENet achieves state-of-the-art results on the 3D benchmark dataset ModelNet.

Both point cloud-based and multi-view-based methods have achieved remarkable results in 3D shape recognition, yet there are few methods that combine the two types of data. In this paper, a novel Global-Local Complementary Network (GLCNet) based on multimodal data is proposed. The network obtains more powerful shape descriptors by stacking multiple layers of Global-Local Complementary Module (GLC Module). More specifically, the Global-Local Relation Score Module is first used to obtain the relationship between view features and global feature. The relationship is then utilized to facilitate the aggregation of view features and to filter out the more important ones. Finally, the aggregated view features are fused with the global features to form a stronger global feature. GLCNet enables the characteristics of various data to be fully utilized and achieves a true sense of complementarity of strengths and weaknesses. Extensive experiments on the benchmark dataset ModelNet show that GLCNet achieves state-of-the-art results in 3D shape classification and retrieval.

Abstract Image segmentation plays a pivotal role in image processing. Level set model is a traditional variation image segmentation method. In order to achieve level set evolution equation, the level set energy functionals are minimized with the gradient descent methods and then the partial differential equation (PDE) was solved by finite difference scheme. Slow speed is one of its disadvantages. We propose a sweep optimization algorithm based on global cosine fitting (GCF) energy. Instead of calculating the PDE and the curvature, the proposed sweeping algorithm directly calculates the energy change when a pixel moves from one side of evolving contour to the other. It checks whether the GCF energy is decreased or not. The proposed algorithm has many advantages. For example, independent of initial level set contour positions and parameters, need not consider the Courant Friedrichs Lew condition and the regularization energy term. The proposed algorithm can be easily extended to high dimension image segmentation. The experiments on synthetic images, noise images and real images demonstrate the effectiveness of the proposed sweeping optimization algorithm.