Human parsing has attracted considerable research interest due to its broad potential applications in the computer vision community. In this paper, we explore several useful properties, including high-resolution representation, auxiliary guidance, and model robustness, which collectively contribute to a novel method for accurate human parsing in both simple and complex scenes. Starting from simple scenes: we propose the boundary-aware hybrid resolution network (BHRN), an advanced human parsing network. BHRN utilizes deconvolutional layers and multi-scale supervision to generate rich high-resolution representations. Additionally, it includes an edge perceiving branch designed to enhance the fineness of part boundaries. Building on BHRN, we construct a dual-task mutual learning (DTML) framework. It not only provides implicit guidance to assist the parser by incorporating boundary features, but also explicitly maintains the high-order consistency between the parsing prediction and the ground truth. Toward complex scenes: we develop a domain transform method to enhance the model robustness. By transforming the input space from the spatial domain to the polar harmonic Fourier moment domain, the mapping relationship to the output semantic space is highly stable. This transformation yields robust representations for both clean and corrupted data. When evaluated on standard benchmark datasets, our method achieves superior performance compared to state-of-the-art human parsing methods. Furthermore, our domain transform strategy significantly improves the robustness of DTML dramatically in most complex scenes.

Drone-based vehicle detection is a critical task within intelligent transportation systems. Existing methods that rely solely on single visible or infrared modalities often struggle to achieve both precise and robust detection. Effectively integrating cross-modal information to assist in vehicle detection remains a significant challenge. In this paper, we propose a Masked-Guided Mamba Fusion (MGMF) method for visible-infrared vehicle detection in aerial scenes. The proposed MGMF framework consists of two key components: the Masked Regularization Constraint Module (MRCM) and the State Space Fusion Module (SSFM). (1) In MAEM, we use candidate regions from one modality to cover corresponding regions of intermediate-level features from another modality, while a regularization constraint extracts cross-modal guidance. This design allows cross-modal features focused on vehicle areas to be extracted from both modalities for fusion. (2) In SSFM, we propose mapping cross-modal features into a shared hidden state for interaction. This reduces disparities between the cross-modal features and enhances the representation, enabling better perception of inter-modal correlations. When evaluated on the DroneVehicle dataset, our MGMF achieves an 80.24% w.r.t. mAP, establishing a new benchmark for state-of-the-art performance. Ablation studies further demonstrate the effectiveness of our MAEM and SSFM in enhancing visible-infrared fusion for vehicle detection.

Background: Clinical notes are documents that contain detailed information about the health status of patients. Medical codes generally accompany them. However, the manual diagnosis is costly and error-prone. Moreover, large datasets in clinical diagnosis are susceptible to noise labels because of erroneous manual annotation. Therefore, machine learning has been utilized to perform automatic diagnoses. Previous state-of-the-art (SOTA) models used convolutional neural networks to build document representations for predicting medical codes. However, the clinical notes are usually long-tailed. Moreover, most models fail to deal with the noise during code allocation. Therefore, denoising mechanism and long-tailed classification are the keys to automated coding at scale.Results: In this paper, a new joint learning model is proposed to extend our attention model for predicting medical codes from clinical notes. On the MIMIC-III-50 dataset, our model outperforms all the baselines and SOTA models in all quantitative metrics. On the MIMIC-III-full dataset, our model outperforms in the macro-F1, micro-F1, macro-AUC, and precision at eight compared to the most advanced models. In addition, after introducing the denoising mechanism, the convergence speed of the model becomes faster, and the loss of the model is reduced overall.Conclusions: The innovations of our model are threefold: firstly, the code-specific representation can be identified by adopted the self-attention mechanism and the label attention mechanism. Secondly, the performance of the long-tailed distributions can be boosted by introducing the joint learning mechanism. Thirdly, the denoising mechanism is suitable for reducing the noise effects in medical code prediction. Finally, we evaluate the effectiveness of our model on the widely-used MIMIC-III datasets and achieve new SOTA results.

To solve the problem of semantic loss in text representation, this paper proposes a new embedding method of word representation in semantic space called wt2svec based on supervised latent Dirichlet allocation (SLDA) and Word2vec. It generates the global topic embedding word vector utilizing SLDA which can discover the global semantic information through the latent topics on the whole document set. It gets the local semantic embedding word vector based on the Word2vec. The new semantic word vector is obtained by combining the global semantic information with the local semantic information. Additionally, the document semantic vector named doc2svec is generated. The experimental results on different datasets show that wt2svec model can obviously promote the accuracy of the semantic similarity of words, and improve the performance of text categorization compared with Word2vec.