To solve the missed and wrong detection problems of the object detection model in identifying soybean companion weeds, this paper proposes an enhanced multi-scale channel feature model based on RT-DETR (EMCF-RTDETR). First, we designed a lightweight hybrid-channel feature extraction backbone network, which consists of a CGF-Block module and a FasterNet-Block module working together, aiming to reduce the amount of computation and the number of parameters while improving the efficiency of feature extraction. Second, we constructed the EA-AIFI module. This module enhances the extraction of detailed features by combining the in-scale feature interaction module with the Efficient Additive attention mechanism. In addition, we designed an Enhanced Multiscale Feature Fusion (EMFF) network structure, which first differentiates the inputs of the three feature layers and then ensures the effective flow between the original and enhanced features of each feature layer by two multiscale feature fusions as well as one diffusion. The experimental results demonstrate that the EMCF-RTDETR model improves the average precision mAP50 and mAP50:95 by 3.3% and 2.2%, respectively, compared to the RT-DETR model, and the FPS is improved by 10%. Moreover, our model outperforms other mainstream detection models in terms of accuracy and speed, revealing its significant potential for soybean weed detection.

Multimodal sentiment analysis must combine textual, visual, and acoustic evidence whose reliability varies across utterances. We propose PGMCR, which uses a predicted three-way polarity distribution to compose sample-level modality-reliability weights and applies a training-only consistency constraint to text-preserving visual and acoustic perturbations. Experiments on CMU-MOSI and CMU-MOSEI show that polarity-guided fusion is the principal architectural contribution, while the text-guided refinement and consistency branch have metric-dependent effects. The learned weights vary across polarity groups, but proxy-corruption diagnostics also reveal strong dependence on textual evidence and non-negligible polarity-estimation errors. The results support polarity as a useful conditioning signal for multimodal fusion while delimiting the scope of the nonverbal robustness claim.

Despite significant advances, multimodal sentiment analysis still faces critical challenges in modeling complex cross-modal interactions and extracting discriminative sentiment features. To address these limitations, this paper proposes a hierarchical multimodal sentiment analysis framework. Specifically, a cross-modal feature enhancement module is first introduced to capture deep correlations among textual, visual, and acoustic modalities via cross-attention mechanisms, thereby obtaining context-aware fused representations. Subsequently, an attention-gated feature disentanglement approach is employed to effectively separate sentiment-relevant information from content-specific features within the fused representations; an independence loss is further imposed to enforce orthogonality between these two feature subsets, thereby mitigating noise induced by repetitive visual frames and textual stop words. Finally, all disentangled features are integrated to facilitate high-level sentiment reasoning through a multimodal logical inference module, where supervised contrastive loss is incorporated to enhance the discriminability of sentiment expressions. Extensive experiments conducted on two public benchmarks, CMU-MOSI and CMU-MOSEI, demonstrate that the proposed framework achieves improvements of 2–6% across multiple evaluation metrics compared with state-of-the-art methods.