Pixel2Mesh (P2M) is a classical approach for reconstructing 3D shapes from a single color image through coarse-to-fine mesh deformation. Although P2M is capable of generating plausible global shapes, its Graph Convolution Network (GCN) often produces overly smooth results, causing the loss of fine-grained geometry details. Moreover, P2M generates non-credible features for occluded regions and struggles with the domain gap from synthetic data to real-world images, which is a common challenge for single-view 3D reconstruction methods. To address these challenges, we propose a novel Transformer-boosted architecture, named T-Pixel2Mesh, inspired by the coarse-to-fine approach of P2M. Specifically, we use a global Transformer to control the holistic shape and a local Transformer to progressively refine the local geometry details with graph-based point upsampling. To enhance real-world reconstruction, we present the simple yet effective Linear Scale Search (LSS), which serves as prompt tuning during the input preprocessing. Our experiments on ShapeNet demonstrate state-of-the-art performance, while results on real-world data show the generalization capability.

Abstract Artificial intelligence decision systems play an important supporting role in the field of medical information. Medical image analysis is an important part of decision systems and an even more important part of medical diagnosis and treatment. The wealth of cellular information in histopathological images makes them a reliable means of diagnosing tumors. However, due to the large size, high resolution, and complex background structure of pathology images, deep learning methods still have various difficulties in the recognition of pathology images. Based on this, this study proposes a two‐stage continuous improvement‐based approach for pathology image recognition in medical decision systems. For pathology images with complex backgrounds, normalization and enhancement is performed to remove the effects of noise color, and light‐dark inconsistencies on the segmentation network. The continuous refinement PSP Net (CRPSPNet) is then designed for accurate recognition of the pathology images. CRPSPNet is divided into two stages: Pyramid Scene Parsing Network segmentation to obtain coarse segmentation results; and continuous refinement model refines the results of the first stage. Experiments using more than 1,000 osteosarcoma pathology images have shown that the method gives more accurate results with fewer computer resources and processing time than traditional optimization models. Its Intersection over Union achieves 0.76.

Abstract Due to the improvement in computing power and the development of computer technology, deep learning has pene‐trated into various fields of the medical industry. Segmenting lesion areas in medical scans can help clinicians make accurate diagnoses. In particular, convolutional neural networks (CNNs) are a dominant tool in computer vision tasks. They can accurately locate and classify lesion areas. However, due to their inherent inductive bias, CNNs may lack an understanding of long‐term dependencies in medical images, leading to less accurate grasping of details in the images. To address this problem, we explored a Transformer‐based solution and studied its feasibility in medical imaging tasks (OstT). First, we performed super‐resolution reconstruction on the original MRI image of osteosarcoma and improved the texture features of the tissue structure to reduce the error caused by the unclear tissue structure in the image during model training. Then, we propose a Transformer‐based method for medical image segmentation. A gated axial attention model is used, which augments existing architectures by introducing an additional control mechanism in the self‐attention module to improve segmentation accuracy. Experiments on real datasets show that our method outper‐forms existing models such as Unet. It can effectively assist doctors in imaging examinations.

Facial attribute recognition is an important and yet challenging research topic. Different from most previous approaches which predict attributes only based on the whole images, this paper leverages facial parts locations for better attribute prediction. A facial abstraction image which contains both local facial parts and facial texture information is introduced. This abstraction image is generated by a Generative Adversarial Network (GAN). Then we build a dual-path facial attribute recognition network to utilize features from the original face images and facial abstraction images. Empirically, the features of facial abstraction images are complementary to features of original face images. With the facial parts localized by the abstraction images, our method improves facial attributes recognition, especially the attributes located on small face regions. Extensive evaluations conducted on CelebA and LFWA benchmark datasets show that state-of-the-art performance is achieved.

A modified interacting multiple model (IMM) method called spherical simplex unscented Kalman filter-based jumping and static IMM (SSUKF-JSIMM) is proposed to solve the problem of nonlinear filtering with unknown continuous system parameter. SSUKF-JSIMM regards the continuous system parameter space as a union of disjoint regions, and each region is assigned to a model. For each model, under the assumption that the parameter belongs to the corresponding region, one sub-filter is used to estimate the parameter and the state when the parameter is presumed to be jumping, and another sub-filter is used to estimate the parameter and the state when the parameter is presumed to be static. Considering that spherical simplex unscented Kalman filter (SSUKF) is more suitable for a real-time system than the unscented Kalman filter (UKF), SSUKFs are adopted as the sub-filters of SSUKF-JSIMM. Results of the two SSUKFs are fused as the estimation output of the model. Experimental results show that SSUKF-JSIMM achieves higher performance than IMM, SIR, and UKF in bearings-only tracking problem.

Deep neural networks have significantly improved the performance of face recognition and facial attribute prediction, which however are still very challenging on the million scale dataset, i.e. MegaFace. In this paper, we for the first time, advocate a multi-task deep neural network for jointly learning face recognition and facial attribute prediction tasks. Extensive experimental evaluation clearly demonstrates the effectiveness of our architecture. Remarkably, on the largest face recognition benchmark -- MegaFace dataset, our networks can achieve the Rank-1 identication accuracy of 77.74% and face verication accuracy 79.24% TAR at 10-6 FAR, which are the best performance on the small protocol among all the publicly released methods.

Multi-task learning aims to boost the performance of multiple prediction tasks by appropriately sharing relevant information among them. However, it always suffers from the negative transfer problem. And due to the diverse learning difficulties and convergence rates of different tasks, jointly optimizing multiple tasks is very challenging. To solve these problems, we present a weighted multi-task deep convolutional neural network for person attribute analysis. A novel validation loss trend algorithm is, for the first time proposed to dynamically and adaptively update the weight for learning each task in the training process. Extensive experiments on CelebA, Market-1501 attribute and Duke attribute datasets clearly show that state-of-the-art performance is obtained; and this validates the effectiveness of our proposed framework.