The proper use of medical personal protective equipment (MPPE) is critical for frontline healthcare workers (HCWs) to handle highly contagious diseases. Due to the complexity of PPE donning and doffing protocols, public health organizations typically recommend having trained observers monitor the entire PPE donning and doffing process, preventing self-contamination and transmission. However, the high costs of manual monitoring impede the implementation of this practice, which makes AI-assisted PPE monitoring highly valuable. Some studies have applied computer vision techniques to PPE monitoring, but they have only focused on limited integrity checks at donning completion, which is unable to provide real-time warnings for abnormal actions during the doffing process. Furthermore, model practicality and user-friendliness are constrained by the lack of explainability. To address this, we propose an explainable and fine-grained dataset for MPPE doffing monitoring called the XFMP dataset. The dataset contains 3596 expert-annotated samples over three sub-tasks: doffing stage classification (DSC), abnormal action recognition (AAR), and critical region localization (CRL). Accordingly, we introduce multi-dimensional evaluation metrics for XFMP and a multitask human behavior semantic attention network (MHBSAN). Experiments demonstrate that MHBSAN outperforms alternative approaches, achieving 0.968/0.855 accuracy for stage/action classification and 0.791 Top-1 [email protected] for CRL sub-task. Moreover, it demonstrates exceptional adaptability across different healthcare environments. Ablation studies and case analyses further validate the contributions and efficacy of the proposed model regarding classification and explainability.

Domain adaptation in person re-identification (re-ID) has always been challenging, especially for the lack of supervision information on the target domain. Existing methods generally introduced extra supervision by adversarial learning techniques, then added all the augmented data in the training process to optimize the re-ID model. However, the direct utilization of all the generated data not only increases additional computational cost but also ignores the potential correlation between the origin and generated data. In this article, we propose a novel dual-alignment learning framework (DAL) with camera-aware image generation to efficiently and effectively tackle this issue. Specifically, we propose a camera transfer matching module to generate additional training images with different camera styles, and construct the matching pairs with each containing a origin image and one corresponding camera transferred image. To strengthen the correlation of images for each matching pair, we align the pseudo-labels via clustering algorithm to reduce the pseudo-labels distribution discrepancy between the origin and generated images. Besides, to avoid model degeneration affected by some inaccurate pseudo-labels on unlabelled data, we maximize the mutual information to align the image feature representations of matching pair. The DAL allows us to decrease the camera variance and enhance the discrimination ability of re-ID model. Extensive experiments on three large-scale benchmarks demonstrate the superiority of DAL over state-of-the-art methods.

Existing successful person re-identification (Re-ID) models often employ the part-level representation to extract the fine-grained information, but commonly use the loss that is particularly designed for global features, ignoring the relationship between semantic parts. In this paper, we present a novel triplet loss that emphasizes the salient parts and also takes the consideration of alignment. This loss is based on the crossing-bing matching metric that also known as Wasserstein Distance. It measures how much effort it would take to move the embeddings of local features to align two distributions, such that it is able to find an optimal transport matrix to re-weight the distance of different local parts. The distributions in support of local parts is produced via a new attention mechanism, which is calculated by the inner product between high-level global feature and local features, representing the importance of different semantic parts w.r.t. identification. We show that the obtained optimal transport matrix can not only distinguish the relevant and misleading parts, and hence assign different weights to them, but also rectify the original distance according to the learned distributions, resulting in an elegant solution for the mis-alignment issue. Besides, the proposed method is easily implemented in most Re-ID learning system with end-to-end training style, and can obviously improve their performance. Extensive experiments and comparisons with recent Re-ID methods manifest the competitive performance of our method.

Weakly supervised learning is capable of achieving fine‐grained tasks with coarse annotations, which has shown great potential in computer‐aided diagnosis. This study aims to achieve thoracic disease diagnosis in a weakly supervised manner only with coarse image‐level annotations. Except for considering the performance of disease diagnosis, the study concentrates more on discovering the location of the pathological area which is used as visualised evidence for interpretability of diagnosis and the following retrospective analysis. To harvest more associated pathological areas, spatial non‐local attention mechanism to learn non‐local aware features is investigated. Further, a simple, effective, and widely applicable model ResNet‐spatial non‐local attention (SNA) is developed for these two objectives. Besides, an effective visualisation method compatible with the proposal is introduced. The effectiveness of the proposed ResNet‐SNA was validated on the large publicly available chest X‐ray dataset, ChestX‐ray14. Compared with the baseline model, the proposed model improved by 7.96% averaged over 14 diseases, achieving 0.8247 area under the scores up to the highest classification results compared with related works. For localisation, the proposed model improved the performance significantly without using any extra information. More importantly, the proposal only requires image‐level annotations without fine‐grained expertise, which is cost‐effective and expected to apply in clinical diagnosis.