technology advancement is inevitable, and it has created a revolution in all the sectors creating huge opportunities. Artificial intelligence and machine learning have boosted the advancement of all the sectors making...
详细信息
This study investigates CPU utilization prediction in cloud environments using the Informer model, a deep learning framework optimized for long-sequence forecasting. By leveraging its ability to capture complex tempor...
详细信息
Current channel assignment techniques rely on the nodes’s decent nature and lack of malicious intent. The accuracy of the information disseminated by the nodes is not confirmed because it is based on an assumption of...
详细信息
Convolutional neural networks (CNNs) and self-attention (SA) have demonstrated remarkable success in low-level vision tasks, such as image super-resolution, deraining, and dehazing. The former excels in acquiring loca...
详细信息
The increasing reliance on online reservation systems across various industries, including hospitality, airlines, and e-commerce, has heightened concerns over last-minute cancellations, may lead to monetary losses and...
详细信息
The demand for high-quality annotated data has surged in recent years for applications driven by real-world artificial intelligence, such as autonomous driving and embodied intelligence. Consequently, the development ...
详细信息
The demand for high-quality annotated data has surged in recent years for applications driven by real-world artificial intelligence, such as autonomous driving and embodied intelligence. Consequently, the development of a tool that can assist humans in the highly automated and high-quality annotation of large-scale, multi-modal data is of significant importance and urgency for both academic research and practical applications. Most existing multi-modal data annotation tools require frame-by-frame, object-by-object annotation with keyboard and mouse, making it challenging to provide high-quality and real-time annotations for 2D images and 3D point clouds in highly open scenarios like autonomous driving. To address these challenges, we propose OpenAnnotate2, which understands human intentions based on natural language prompt, and formulates plans to decompose and execute complex multi-modal data annotation tasks. Additionally, the tool can continually enhance its cognitive and annotation capabilities with minimal human-computer interaction, through an ever-updating external knowledge base. This significantly simplifies the annotation workflow, paving the way for the creation of massive datasets suitable for large-scale visual models. The source code will be released at https://***/Fudan-ProjectTitan/OpenAnnotate. IEEE
Point cloud completion concentrates on completing geometric and topological shapes from incomplete 3D shapes. Nevertheless, the unordered nature of point clouds will hamper the generation of high-quality point clouds ...
详细信息
Point cloud completion concentrates on completing geometric and topological shapes from incomplete 3D shapes. Nevertheless, the unordered nature of point clouds will hamper the generation of high-quality point clouds without predicting structured and topological information of the complete shapes and introducing noisy points. To effectively address the challenges posed by missing topology and noisy points, we introduce SPOFormer, a novel topology-aware model that utilizes surface-projection optimization in a progressive growth manner. SPOFormer consists of three distinct steps for completing the missing topology: (1) Missing Keypoints Prediction. A topology-aware transformer auto-encoder is integrated for missing keypoint prediction. (2) Skeleton Generation. The skeleton generation module produces a new type of representation named skeletons with the aid of keypoints predicted by topology-aware transformer auto-encoder and the partial input. (3) Progressively Growth. We design a progressive growth module to predict final output under Multi-scale Supervision and Surface-projection Optimization. Surface-projection Optimization is firstly devised for point cloud completion, aiming to enforce the generated points to align with the underlying object surface. Experimentally, SPOFormer model achieves an impressive Chamfer Distance-$\ell _{1}$ (CD) score of 8.11 on PCN dataset. Furthermore, it attains average CD-$\ell _{2}$ scores of 1.13, 1.14, and 1.70 on ShapeNet-55, ShapeNet-34, and ShapeNet-Unseen21 datasets, respectively. Additionally, the model achieves a Maximum Mean Discrepancy (MMD) of 0.523 on the real-world KITTI dataset. These outstanding qualitative and quantitative performances surpass previous approaches by a significant margin, firmly establishing new state-of-the-art performance across various benchmark datasets. Our code is available at https://***/kiddoray/SPOFormer IEEE
Complex networking analysis is a powerful technique for understanding both complex networks and big graphs in ubiquitous computing. Particularly, there are several novel metrics, such as k-clique and k-core are propos...
详细信息
Sustainable development is crucial for a prosperous future, but epidemic diseases like Coronavirus Disease 2019 (COVID-19) pose real and complex challenges. The global pandemic, declared by the WHO on March 11, 2020, ...
详细信息
Breast cancer in women’s becoming the serious cause moving to the morbidity and the mortality worldwide. This paper aims to design the hybrid model using various machine learning classification algorithms like k-Near...
详细信息
暂无评论