Generating radiology reports automatically reduces the workload of radiologists and helps the diagnoses of specific diseases. Many existing methods take this task as modality transfer process. However, since the key information related to disease accounts for a small proportion in both image and report, it is hard for the model to learn the latent relation between the radiology image and its report, thus failing to generate fluent and accurate radiology reports. To tackle this problem, we propose a memory-based cross-modal semantic alignment model (MCSAM) following an encoder-decoder paradigm. MCSAM includes a well initialized long-term clinical memory bank to learn disease-related representations as well as prior knowledge for different modalities to retrieve and use the retrieved memory to perform feature consolidation. To ensure the semantic consistency of the retrieved cross modal prior knowledge, a cross-modal semantic alignment module (SAM) is proposed. SAM is also able to generate semantic visual feature embeddings which can be added to the decoder and benefits report generation. More importantly, to memorize the state and additional information while generating reports with the decoder, we use learnable memory tokens which can be seen as prompts. Extensive experiments demonstrate the promising performance of our proposed method which generates state-of-the-art performance on the MIMIC-CXR dataset.

Skeleton-based human action recognition has made great progress, especially with the development of a graph convolution network (GCN). The most important work is ST-GCN, which automatically learns both spatial and temporal patterns from skeleton sequences. However, this method still has some imperfections: only short-range correlations are appreciated, due to the limited receptive field of graph convolution. However, long-range dependence is essential for recognizing human action. In this work, we propose the use of a spatial-temporal relative transformer (ST-RT) to overcome these defects. Through introducing relay nodes, ST-RT avoids the transformer architecture, breaking the inherent skeleton topology in spatial and the order of skeleton sequence in temporal dimensions. Furthermore, we mine the dynamic information contained in motion at different scales. Finally, four ST-RTs, which extract spatial-temporal features from four kinds of skeleton sequence, are fused to form the final model, multi-stream spatial-temporal relative transformer (MSST-RT), to enhance performance. Extensive experiments evaluate the proposed methods on three benchmarks for skeleton-based action recognition: NTU RGB+D, NTU RGB+D 120 and UAV-Human. The results demonstrate that MSST-RT is on par with SOTA in terms of performance.

Monocular 3D object detection plays a pivotal role in autonomous driving, presenting a formidable challenge by requiring the precise localization of 3D objects within a single image, devoid of depth information. Most existing methods in this domain fall short of harnessing the limited information available in monocular 3D detection tasks. They typically provide only a single detection outcome, omitting essential uncertainty analysis and result post-processing during model inference, thus limiting overall model performance. In this paper, we propose a comprehensive framework that maximizes information extraction from monocular images while encompassing diverse depth estimation and incorporating uncertainty analysis. Specifically, we mine additional information intrinsic to the monocular 3D detection task to augment supervision, thereby addressing the information scarcity challenge. Moreover, our framework handles depth estimation by recovering multiple sets of depth values from calculated visual heights. The final depth estimate and 3D confidence are determined through an uncertainty fusion process, effectively reducing inference errors. Furthermore, to address task weight allocation in multi-task training, we present a versatile training strategy tailored to monocular 3D detection. This approach leverages measurement indicators to monitor task progress, adaptively adjusting loss weights for different tasks. Experimental results on the KITTI and Waymo dataset confirm the effectiveness of our approach. The proposed method consistently provides enhanced performance across various difficulty levels compared to the original framework while maintaining real-time efficiency.

Objective: This study aimed to investigate the antimicrobial susceptibilities, drug resistance mechanisms, and biofilm formation capacities of non-diphtheriae Corynebacterium strains isolated from sterile midstream urine of hospitalized patients with clinical urinary tract infections (UTIs). Methods: A total of 45 non-diphtheriae Corynebacterium isolates were recovered from sterile midstream urine. The available data of 45 patients were collected. Minimum inhibitory concentrations (MICs) of 10 commonly used antibiotics were determined. Meanwhile, the molecular resistance mechanisms of each agent were performed through PCR with specific primers. Moreover, the biofilm formation capability of each isolate on abiotic surfaces was detected with the MTT method. Results: In this study, the most prevalent three species were C. striatum (15/45, 33.3%), C. glucuronolyticum (9/45, 20.0%) and C. urealyticum (8/45, 17.8%). These three species also accounted for most renal and ureteral calculi cases. Male patients older than 50 years, especially those with underlying diseases, were more susceptible to non-diphtheriae Corynebacterium infection. All the 45 isolates were 100% susceptible to vancomycin and linezolid, but highly resistant to macrolide–lincosamide–streptogramin B (MLSB), fluoroquinolones, tetracyclines and β-lactams with corresponding mechanisms. The detection rate of multidrug–resistant (MDR) non-diphtheriae Corynebacterium is 91.1%. All isolates are able to form biofilm on abiotic surfaces, except those of C. urealyticum, C. tuberculostearicum and C. jeikeium. Isolates of C. glucuronolyticum and C. Striatum possessed the strongest biofilm formation capacity. C. amycolatum could form biofilm, but varied greatly among different isolates. Conclusion: C. striatum, C. glucuronolyticum and C. urealyticum were the most prevalent species relevant to UTIs. The high occurrence of MDR isolates and high diversities in resistance profiles, and the distinctive abilities of biofilm formation highlighted the urgency for identification to species level. We should pay more attention to the drug resistance profiles of non-diphtheriae Corynebacterium, which would help improve empirical antibiotic therapy and reduce drug resistance transmission.

Due to the overarching similarities of ships, subtle information is imperative for fine-grained ship detection. However, this information is easily lost in adverse weather (e.g., fog, rain, snow, and cloud) or occlusion scenarios. Experts can quickly and accurately recognize fine-grained objects because they have the domain knowledge to help them find the most discriminative information (e.g., edge, structure, texture, and class semantics); thus, they do not need a lot of information to make an identification. Motivated by it, we propose a discriminative information enhancement method with cross-modal domain knowledge (DIE-CDK) for fine-grained ship detection. The core idea behind DIE-CDK is to enhance the discriminative information about fine-grained ships by fusing cross-modal domain knowledge. The introduced cross-modal domain knowledge comprises local and global knowledge: 1) local knowledge is the knowledge of visual shape (e.g., edge contour) which is extracted from the image domain; and 2) global knowledge is the knowledge of the class semantics which is obtained from the common sense domain. In addition, to further study fine-grained ship detection, we introduce a Fine-grained ship dataset (called FgShips). Experiments show that our proposed DIE-CDK method achieves impressive gains in detection performance and outperforms state-of-the-art methods on fine-grained ship and public datasets.