BACKGROUND: While the RNA-binding protein HuR is implicated in individual cancers, its comprehensive diagnostic, prognostic, and immunological roles across diverse cancer types remain unexplored. METHODS: We performed an integrated pan-cancer analysis of HuR using public datasets. This encompassed expression profiling, survival analysis, diagnostic accuracy assessment, immune microenvironment characterization, and drug sensitivity prediction. We investigated HuR's regulatory mechanisms through pathway correlation and differential gene expression analyses. RESULTS: HuR expression was consistently elevated across multiple cancers and correlated with poor patient prognosis. It demonstrated high diagnostic accuracy (>85%) via TMB/PD-L1 biomarkers. High HuR expression was associated with an immunosuppressive tumor microenvironment and reduced efficacy of immune checkpoint inhibitors, establishing it as a key immunoregulatory biomarker. HuR also predicted sensitivity to cell cycle inhibitors and other pathway-targeted drugs. Mechanistically, HuR drives malignancy by dysregulating core processes: cell cycle progression, immune evasion, and cellular metabolism. CONCLUSIONS: Our pan-cancer analysis establishes HuR as a consistently upregulated oncogenic driver across malignancies, functioning as a potential universal biomarker for prognosis and diagnosis. Its critical roles in modulating the immune response and predicting therapeutic sensitivity highlight its importance for personalized cancer treatment strategies. HuR orchestrates tumorigenesis and malignant progression by integrally regulating vital cellular processes.

Radiology report generation can simulate the diagnostic process of doctors. Automatically generate diagnostic reports has attracted more and more attention from researchers in recent years. However, existing report generation methods based on the encoder-decoder framework mainly choose convolutional neural networks (CNNs) as image feature extractors and transformers as decoder. To address the problems that a single image encoder cannot effectively alleviate the visual-textual cross-modal semantic gap and that traditional transformer cannot capture enough long-term dependencies, which leads to poor report generation quality, in this paper, we propose a framework for radiology report generation that achieves long-term memory transformer with visual-textual cross-fusion. Large vision-and-language pretraining (VLP) models are used to obtain visual and textual representations containing rich multimodal knowledge. A cross-fusion module is used to achieve deep interaction between visual and textual representations, aiming at exploring the subtle interactions between visual and textual representations. Thus complex cross-modal generation capabilities are enhanced. The memory module saves the global and the previous information, which is convenient for the model to integrate the global and the previous information in the decoding process, and better capture the long-term dependency relationships. Experiments on the IU X-Ray dataset and MIMIC-CXR dataset show that our approach significantly improves the accuracy of report generation, achieving advanced results on several evaluation metrics and demonstrating superior performance.

Multi-person pose estimation is a challenging task which aims to locate keypoints for multiple persons. Graph convolutional network can effectively capture the semantic relationship among keypoints according to the kinematic structure of the human body, which is beneficial to locate keypoints but is the lack of ability of most CNN-based models. However, existing GCN-based methods mostly flatten the 2D features directly to obtain 1D embeddings, leading to the redundant information in keypoints embeddings, large size of keypoints embeddings, and high computation cost. To address these problems, we propose a two-stage framework based on Heatmaps-guided Keypoints Encoder and graph convolutional network, called HKE-GCN. The first stage uses a heatmaps-based network to predict the heatmaps of keypoints, then the second stage refines the prediction of the first stage. The second stage consists of two modules: Heatmaps-guided Keypoints Encoder (HKE) and Graph-based Refinement Module (GRM), which are used to generate keypoints embeddings according to the guidance of heatmaps and explicitly learn the relationship among keypoints based on GCN, respectively. Experiments show our framework is model-agnostic and our proposed modules are effective and lightweight. Our best model achieves state-of-the-art 76.4AP on COCO test-dev.

Recently, the performance of super-resolution has been improved by the stereo images since the additional information could be obtained from another view. However, it is a challenge to interact the cross-view information since disparities between left and right images are variable. To address this issue, we propose a disparity feature alignment module (DFAM) to exploit the disparity information for feature alignment and fusion. Specifically, we design a modified atrous spatial pyramid pooling module to estimate disparities and warp stereo features. Then we use spatial and channel attention for feature fusion. In addition, DFAM can be plugged into an arbitrary SISR network to super-resolve a stereo image pair. Extensive experiments demonstrate that DFAM incorporates stereo information with less inference time and memory cost. Moreover, RCAN equipped with DFAMs achieves better performance against state-of-the-art methods. The code can be obtained at https://github.com/JiawangDan/DFAM.

The architecture of the convolutional neural network (CNN) plays an important role in single image super-resolution (SISR). However, most models proposed in recent years usually transplant methods or architectures that perform well in other vision fields. Thence they do not combine the characteristics of super-resolution (SR) and ignore the key information brought by the recurring texture feature in the image. To utilize patch-recurrence in SR and the high correlation of texture, we propose a residual fractal convolutional block (RFCB) and expand its depth and width to obtain residual fractal network (RFN), which contains two variations, deep residual fractal network (DRFN) and wide residual fractal network (WRFN). RFCB is recursive with multiple branches of magnified receptive field. Through the phased feature fusion module, the network focuses on extracting high-frequency texture feature that repeatedly appear in the image. We also introduce residual in residual (RIR) structure to RFCB that enables abundant low-frequency feature feed into deeper layers and reduce the difficulties of network training. RFN is the first supervised learning method to combine the patch-recurrence characteristic in SISR into network design. Extensive experiments demonstrate that RFN outperforms state-of-the-art SISR methods in terms of both quantitative metrics and visual quality, while the amount of parameters has been greatly optimized. The source code and pre-trained models are released in https://github.com/JiahangGu/RFN.

Video captioning is one of research hotspots in computer vision. At present, video captioning algorithms mainly have following problems: First, traditional algorithms use equal-interval sampling to extract video features, which causes the loss of key frames containing a large amount of semantic information, thus leading to the inaccuracy of video captioning. Moreover, equal-interval sampling method results in lots of redundant frames, thereby increasing the amount of computation of algorithms extremely. Second, traditional algorithms only consider temporal information when extracting features. However, for the image and video, the spatial features also contain rich latent semantic information. Only extracting temporal features will lead to inaccurate natural language descriptions. To address these problems, we propose the video captioning method based on key semantic frames extraction and spatio-temporal attention mechanism (KSF-ST) in this paper. In order to extract key semantic frames, knowledge graph is adopted to obtain key semantic information of video frames, and knowledge reasoning is used to obtain the correlation among entities in the knowledge graph. In order to extract spatial latent semantic information of video frames, spatial attention mechanism is combined with temporal features to generate accurate natural language descriptions. We evaluate KSF-ST on two benchmark datasets. Extensive experiments have been conducted and the results demonstrate that our algorithm could achieve better video captioning performance than the state-of-the-art algorithms.

Images are complex multimedia data that contain rich semantic information. Currently, most of image annotation algorithms are only annotating the object semantics of images. There are still many challenges on high-level semantic image annotation. The major issues are the lack of effective modeling method for the high-level semantics of images and the lack of efficient dynamic update mechanism for the training set. To address these issues, we propose a high-level semantic annotation method based on hot Internet topics in this paper. There are two independent sub tasks in our method: dynamic update of the training set based on hot Internet topics and search-based image annotation. In the first sub task, we propose to model the abstract semantics of images based on three relationships: image–to–image similarity relationship, topic–to–topic co-occurrence relationship, and image–to–topic relevance relationship. Through the complex graph clustering, the hot Internet topics are extracted for images with consistent visual and semantic contents. Then the dynamic update mechanism will update the original training set with the new topics and images. It avoids the huge computing cost in traditional update methods and does not need to re-calculate the whole mapping relationship between the semantic concepts and visual features. In the second sub task, given a query image, it first searches for similar candidates in the annotated training set via visual features. Then the hypergraph modeling and spectral clustering are exploited to filter out the images with irrelevant semantics. The keywords will be extracted for annotation from the remaining images according to an annotation probability. Extensive experiments have been conducted and the results demonstrate that our algorithm could achieve better annotation performance than the state-of-the-art algorithms. And the update mechanism could extend the training set efficiently so that the coverage of the semantics in the training set wouldn’t be obsolete.

Power systems get more unstable and insecure with more transmission congestion and smaller generation reserves. There is prospect of wide area control schemes meeting the challenge instead of traditional local ones. Communication network technologies, which have made a great stride during last decade, play an important role in the new schemes. Control systems based on wide area networks (WAN) are studied in this paper. Multi-agent concept is introduced to improve the control performance. A novel wide-area control system that utilizes phasor measurement unit (PMU), wide-area communication and multi-agent technology is presented. The distributed system architecture and multi-agent working mechanism are discussed in order to use phasor data and to realize optimal power system stability control.

In this paper, support vector machines (SVMs) are studied in the application of transient stability assessment in power systems. SVMs have the following advantages: automatic determination of the number of hidden neurons, fast convergence rate, good generalization capability, etc. SVMs use the principle of structural risk minimization, and thus reduce the dependency of experience unlike neural networks and have better generalization and classification precision. Furthermore, SVMs are solved by the 2nd order convex programming and the final solution of SVMs is sole and optimal. The performance of SVMs depends on the type of kernel functions and the parameters of kernel functions, which are determined by experience or experiments. So the effects of kernel functions and the parameters of kernel functions are analyzed by experiments in the paper. In addition, Experiments corroborate the superiority of v-SVM applied in TSA in power systems by comparing with BP and RBE.