最新刊期
- 摘要：Multimodal emotion recognition has broad applications in psychological health monitoring and affective computing. However, most existing studies rely on either global or local features, neglecting the joint modeling of both, which limits performance. To address this, a dual-stage gated segmented fusion architecture is proposed, consisting of an interaction stage and a dual-stage gating stage. The interaction stage leverages the OAGL fusion strategy to model global-local cross-modal interactions, improving the efficiency of feature fusion. The dual-stage gating stage integrates local and global features to fully utilize emotional information. Additionally, to resolve the misalignment of local temporal features across modalities, a scaled dot-product-based sequence alignment method is designed to enhance fusion accuracy. Experimental results demonstrate that the proposed method outperforms representative algorithms on multiple datasets, validating its ability to capture emotional details and its strong generalization capability.关键词：Multimodal Emotion Recognition;Scaled Dot-Product Attention;Dual-Stage Gated Fusion;Transformer80|135|0更新时间：2025-05-07
- 摘要：Facing the problem of satellite navigation spoofing interference detection, this paper proposes a feature parameter selection and data processing method applicable to the detection of spoofing interference by Long Short-term Memory (LSTM) neural network. Based on the analysis of the effect of spoofing interference on the receiver loop, the direct and indirect information in the tracking loop is selected as the spoofing detection feature parameters; the feature parameters are preprocessed using the sliding window technique, and the training and test sets are constructed according to the time series to ensure the temporal relevance of the features. Based on the experiments conducted on the TEXBAT dataset from the University of Texas at Austin, this paper's method can improve the accuracy of spoofing detection by 2.19% and spoofing scene recognition by 99.98% compared to the existing SVM methods, which can effectively solve the problem of navigation spoofing detection and scene recognition.关键词：satellite navigation;spoofing interference;sliding window processing;long and short-term memory neural networks157|191|0更新时间：2025-05-07
- 摘要：To address the challenges of image complexity, limited textual information, and inter-modal misleading data in cross-modal emergency recognition, this paper proposes a novel fusion recognition method that integrates attentional collaboration and contrastive learning. First, a multi-branch self-attention mechanism is integrated into an image feature encoder, while a text feature encoder is augmented with external knowledge. These encoders are designed to extract rich semantic features from images and contextual information from text, respectively, for overcoming the limitations of single-modal representations. Next, a cross-modal attentional collaboration network is introduced to capture intricate relationships between image-text features, enhancing inter-modal consistency and mitigating the influence of misleading information. Finally, a contrastive learning mechanism, that is optimized through a joint supervision strategy, is employed to dynamically balance the contributions of image and text features. Extensive experiments conducted on the public CrisisMMD dataset and the self-constructed dataset demonstrate the superior performance of the proposed method.关键词：Emergency recognition;Cross-modal;Attention collaboration;Contrastive learning66|10|0更新时间：2025-05-07
- 摘要：Lip reading technology establishes the mapping relationship between lip movements and specific language characters by processing a series of consecutive lip images, thereby enabling semantic information recognition. Existing methods mainly use recurrent networks for spatiotemporal modeling of sequential video frames. However, they suffer from significant information loss, especially when the video information is incomplete or contains noise. In such cases, the model often struggles to distinguish between lip movements at different time points, leading to a significant decline in recognition performance. To address this issue, a lip reading method based on Adaptive Pooling Attention Transformer (APAT-LR) is proposed. This method introduces an Adaptive Pooling Module before the Multi-Head Self-Attention (MHSA) mechanism in the standard Transformer, using a concatenation strategy of max pooling and average pooling. This module helps suppress irrelevant information and enhances the representation of key features. Experiments on the CMLR and GRID datasets show that the proposed APAT-LR method can reduce the recognition error rate, thus verifying the effectiveness of the proposed method.关键词：attention mechanism;Transformer;Convolutional Pooling;Adaptive210|195|0更新时间：2025-05-07
- 摘要：In the complex real-world applications, the task of detecting small faces encounters numerous challenges, which include issues related to scale variation, abrupt lighting changes and suboptimal precision. In order to address the concerns of overlooking small facial structures within existing models, this study introduces a novel approach termed SK-YOLOv5s which is based on convolutional kernel attention mechanism. Firstly, we proposal a small face enhancement module to fuse multi-layer features, which can enhance the resolution of small faces and improve its features.Subsequently, we incorporates SKNet attention mechanism into the model to adaptively adjust receptive field sizes across multiple scales so that the detection efficacy of small face can be enhanced. Finally, EIoU is utilized as the loss function, which facilitate a direct optimization of the width and height discrepancies between predicted and actual bounding boxes. This approach enhances the precision and stability of small face detection. The performance on the WIDER Face dataset demonstrate a mean detection accuracy improvement of 3.1% over prevailing methods. The experimental results demonstrate the model's viability for detecting small faces in real-life scenarios.关键词：Small Face Detection;attention mechanism;YOLOv5s122|186|0更新时间：2024-11-05
- Postal code：100079
- Tel：（010）53879206 Email：cjist@bjxintong.com.cn
- Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
- Total Visits：185511 Visits Today：506
0