Chenquan Gan^1,2,*, Xu Liu¹, Yu Tang², Xianrong Yu³, Qingyi Zhu¹, Deepak Kumar Jain⁴

CMC-Computers, Materials & Continua, Vol.85, No.3, pp. 5399-5421, 2025, DOI:10.32604/cmc.2025.068126 - 23 October 2025

Abstract Multimodal sentiment analysis aims to understand emotions from text, speech, and video data. However, current methods often overlook the dominant role of text and suffer from feature loss during integration. Given the varying importance of each modality across different contexts, a central and pressing challenge in multimodal sentiment analysis lies in maximizing the use of rich intra-modal features while minimizing information loss during the fusion process. In response to these critical limitations, we propose a novel framework that integrates spatial position encoding and fusion embedding modules to address these issues. In our model, text is… More >

Ziwei Tang¹, Yaohua Yi^2,*, Changhui Yu², Aiguo Yin³

CMC-Computers, Materials & Continua, Vol.75, No.3, pp. 6007-6022, 2023, DOI:10.32604/cmc.2023.037861 - 29 April 2023

Abstract Existing image captioning models usually build the relation between visual information and words to generate captions, which lack spatial information and object classes. To address the issue, we propose a novel Position-Class Awareness Transformer (PCAT) network which can serve as a bridge between the visual features and captions by embedding spatial information and awareness of object classes. In our proposal, we construct our PCAT network by proposing a novel Grid Mapping Position Encoding (GMPE) method and refining the encoder-decoder framework. First, GMPE includes mapping the regions of objects to grids, calculating the relative distance among… More >

Tianyu Liu^1,3,4, Pengyu Liu^1,2,3,4,*, Xiaowei Jia⁵, Shanji Chen², Ying Ma², Qian Gao^1,3,4

Computer Systems Science and Engineering, Vol.45, No.2, pp. 1033-1045, 2023, DOI:10.32604/csse.2023.028225 - 03 November 2022

Abstract Image segmentation of sea-land remote sensing images is of great importance for downstream applications including shoreline extraction, the monitoring of near-shore marine environment, and near-shore target recognition. To mitigate large number of parameters and improve the segmentation accuracy, we propose a new Squeeze-Depth-Wise UNet (SDW-UNet) deep learning model for sea-land remote sensing image segmentation. The proposed SDW-UNet model leverages the squeeze-excitation and depth-wise separable convolution to construct new convolution modules, which enhance the model capacity in combining multiple channels and reduces the model parameters. We further explore the effect of position-encoded information in NLP (Natural… More >