In multimodal sentiment analysis, a significant challenge lies in quantifying the contribution of each modality and achieving effective modality fusion. This paper presents a Hierarchical Gating-Driven Transformer Fusion Model (HGTFM), which effectively achieves multimodal data fusion through an advanced transformer architecture and a Hierarchical Gated Fusion Module (HGFM). The model first encodes audio and video features using LSTM and CNN, respectively, while employing BERT to encode text features. This approach effectively enhances the model ability to manage long-range temporal dependencies. Furthermore, the model introduces HGFM, which dynamically integrates multimodal features across different levels after processing by the modality interaction network (MIN), thus intelligently adjusting the contribution weights of each modality. In particular, the model incorporates a Unimodal Label Generation Module (ULGM), which considers the differences between the modalities. This enables HGFM to more accurately identify the contributions of samples with significant modal variations, thus optimizing the module potential. The experimental results on several established benchmark datasets demonstrate that HGTFM achieves comparable performance improvements in multimodal sentiment analysis tasks.

Multimodal sentiment analysis (MSA) faces key challenges such as incomplete modality inputs, long-range temporal dependencies, and suboptimal fusion strategies. To address these, we propose MGMR-Net, a Mamba-guided multimodal reconstruction and fusion network that integrates modality-aware reconstruction with text-centric fusion within an efficient state-space modeling framework. MGMR-Net consists of two core components: the Mamba-collaborative fusion module, which utilizes a two-stage selective state-space mechanism for fine-grained cross-modal alignment and hierarchical temporal integration, and the Mamba-enhanced reconstruction module, which employs continuous-time recurrence and dynamic gating to accurately recover corrupted or missing modality features. The entire network is jointly optimized via a unified multi-task loss, enabling simultaneous learning of discriminative features for sentiment prediction and reconstructive features for modality recovery. Extensive experiments on CMU-MOSI, CMU-MOSEI, and CH-SIMS datasets demonstrate that MGMR-Net consistently outperforms several baseline methods under both complete and missing modality settings, achieving superior accuracy, robustness, and generalization.

Tomato leaf diseases cause substantial yield and quality losses worldwide, yet reliable detection in real fields remains challenging. Two practical bottlenecks dominate current research: (i) limited data, including small samples for rare diseases, class imbalance, and noisy field images, and (ii) multimodal heterogeneity, where RGB images, textual symptom descriptions, spectral cues, and optional molecular assays provide complementary but hard-to-align evidence. This review summarizes recent advances in tomato leaf disease detection under these constraints. We first formalize the problem settings of limited and multimodal data and analyze their impacts on model generalization. We then survey representative solutions for limited data (transfer learning, data augmentation, few-/zero-shot learning, self-supervised learning, and knowledge distillation) and multimodal fusion (feature-, decision-, and hybrid-level strategies, with attention-based alignment). Typical model–dataset pairs are compared, with emphasis on cross-domain robustness and deployment cost. Finally, we outline open challenges—including weak generalization in complex field environments, limited interpretability of multimodal models, and the absence of unified multimodal benchmarks—and discuss future opportunities toward lightweight, edge-ready, and scalable multimodal systems for precision agriculture.

Accurate identification of weed species is a fundamental task for promoting efficient farmland management. Existing recognition approaches are typically based on either conventional Convolutional Neural Networks (CNNs) or the more recent Vision Transformers (ViTs). CNNs demonstrate strong capability in capturing local spatial patterns, yet they are often limited in modeling long-range dependencies. In contrast, ViTs can effectively capture global contextual information through self-attention, but they may neglect fine-grained local features. These inherent shortcomings restrict the recognition performance of current models. To overcome these limitations, we propose a lightweight hybrid architecture, termed RepEfficientViT,which integrates convolutional operations with Transformer-based self-attention. This design enables the simultaneous aggregation of both local details and global dependencies. Furthermore, we employ a structural re-parameterization strategy to enhance the representational capacity of convolutional layers without introducing additional parameters or computational overhead. Experimental evaluations reveal that RepEfficientViT consistently surpasses state-of-the-art CNN and Transformer baselines. Specifically, the model achieves an accuracy of 94.77%, a precision of 94.75%, a recall of 94.93%, and an F1-score of 94.84%. In terms of efficiency, RepEfficientViT requires only 223.54 M FLOPs and 1.34 M parameters, while attaining an inference latency of merely 25.13 ms on CPU devices. These results demonstrate that the proposed model is well-suited for deployment in edge-computing scenarios subject to stringent computational and storage constraints.

The timely and correct identification of rice diseases is essential to ensuring rice productivity. However, many methods have drawbacks such as slow recognition speed, low recognition accuracy and overly complex models that are unfavorable for portability. Therefore, this study proposes an improved model for accurately classifying rice diseases based on a two-level routing attention mechanism and dynamic convolution based on the above difficulties. The model employs Alterable Kernel Convolution with dynamic, irregularly shaped convolutional kernels and Bi-level Routing Attention that utilizes sparsity to reduce parameters and involves a GPU-friendly dense matrix multiplication, which can achieve high-precision rice disease recognition while ensuring lightweight and recognition speed. The model successfully classified 10 species, including nine diseased and healthy rice, with 97.31% accuracy and a 97.18% F1-score. Our proposed method outperforms MobileNetV3-large, EfficientNet-b0, Swin Transformer-tiny and ResNet-50 by 1.73%, 1.82%, 1.25% and 0.67%, respectively. Meanwhile, the model contains only $4.453\times {10}^6$ parameters and achieves an inference time of 6.13 s, which facilitates deployment on mobile devices.The proposed MobileViT_BiAK method effectively identifies rice diseases while providing a lightweight and high-performance classification solution.