检索结果-内蒙古大学图书馆

Transbuilding: An End-to-End Polygonal Building Extraction with Transformers

学校读者我要写书评

暂无评论

Transbuilding: An End-to-End Polygonal Building Extraction w...

IEEE International Conference on Image Processing

作者： Mingming Zhang Qingjie Liu Wei Wang Yunhong Wang State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Hangzhou Innovation Institute Beihang University National Disaster Reduction Center of China The Ministry of Emergency Management of China

In this paper, we propose a simple yet powerful network, called TransBuilding, for high-quality polygonal building extraction from remote sensing images. Unlike many previous methods that vectorize building masks through mask refinement and fitting or vertex prediction and assembling, our approach predicts the building vertex sequence with a vertex transformer (termed as VertexFormer) branch without any additional processing. The VertexFormer branch represents a polygon as a Bi-directional Ring without start or end vertex hypothesis, which leads to a simple and elegant representation of polygons avoiding ambiguous of defining the start vertex in polygons. Furthermore, three self-attention modules in row-wise, column-wise, and vertex-wise are integrated in parallel together to better capture geometric structures of building polygons. We graft the VertexFormer module onto the standard Faster RCNN detector and train the model end-to-endly using the novel Bi-Ring loss developed by the new perspective of Bi-directional Ring. Extensive experiments on the benchmark CrowdAI dataset demonstrate that our method outperforms state-of-the-art methods by considerable margins.

关键词：

Morphology and Volume Estimation of the Amniotic Sac Based on MRI Image Analysis: Construction of a Knowledge Graph for Risk Assessment of Premature Rupture of Membranes

学校读者我要写书评

暂无评论

SSRN

SSRN 2025年

作者： Zhang, Tong Zhang, Yan Li, Shuai Cheng, Yongfeng Xiao, Yuntian Zhao, Zilong Institute of Solid Mechanics School of Aeronautics Sciences and Engineering Beihang University Beijing100083 China Obstetrics and Gynecology Department Peking University Third Hospital Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China

Achieving the quantification of the amniotic sac's volume and the visualization of its morphology provides a starting point for constructing the PROM knowledge ***, the Magnetic Resonance Imaging (MRI) scan data is imported into the Segment Anything Model (SAM), where region segmentation is performed through semi-automatic point selection. Through volume visualization, a high-resolution, voxel-based 3D reconstruction of the amniotic membrane with a smooth surface is obtained. The high-fidelity surface shape of the amniotic membrane can be well observed by the visualization of voxel data. An edge detection algorithm is applied, voxel integration is used to calculate an approximate digital volume of the amniotic sac. Finally, mathematical methods and techniques are applied to the identified edge curves to establish a semi-empirical formula for estimating the volume of the amniotic sac. Five approximate digital volumes were calculated using the SAM and considered as reference values. A comparison of the results from the semi-empirical formula with the reference values reveals a maximum error rate of 14%, a minimum error rate of 6%, and an average error rate of 10%. These results highlight the high accuracy, simplicity, and efficiency of the semi-empirical formula. Furthermore, a high-level hierarchical framework for constructing the risk assessment knowledge graph of PROM is proposed. Develop a multi-hierarchical knowledge graph framework for assessing the risk of premature rupture of membranes, offering both theoretical support and technical assurance for personalized risk evaluation, data-driven decision-making, systematic diagnostic and treatment processes, and visualized analysis. This will foster the precision, standardization, and intelligent application of clinical practices. © 2025, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

SparseTT: Visual Tracking with Sparse Transformers

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Fu, Zhihong Fu, Zehua Liu, Qingjie Cai, Wenrui Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Hangzhou Innovation Institute Beihang University Beijing China

Transformers have been successfully applied to the visual tracking task and significantly promote tracking performance. The self-attention mechanism designed to model long-range dependencies is the key to the success of Transformers. However, self-attention lacks focusing on the most relevant information in the search regions, making it easy to be distracted by background. In this paper, we relieve this issue with a sparse attention mechanism by focusing the most relevant information in the search regions, which enables a much accurate tracking. Furthermore, we introduce a double-head predictor to boost the accuracy of foreground-background classification and regression of target bounding boxes, which further improve the tracking performance. Extensive experiments show that, without bells and whistles, our method significantly outperforms the state-of-the-art approaches on LaSOT, GOT-10k, TrackingNet, and UAV123, while running at 40 FPS. Notably, the training time of our method is reduced by 75% compared to that of TransT. The source code and models are available at https://***/fzh0917/SparseTT. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

PANFORMER: A TRANSFORMER BASED MODEL FOR PAN-SHARPENING

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhou, Huanyu Liu, Qingjie Wang, Yunhong The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

Pan-sharpening aims at producing a high-resolution (HR) multi-spectral (MS) image from a low-resolution (LR) multi-spectral (MS) image and its corresponding panchromatic (PAN) image acquired by a same satellite. Inspired by a new fashion in recent deep learning community, we propose a novel Transformer based model for pan-sharpening. We explore the potential of Transformer in image feature extraction and fusion. Following the successful development of vision transformers, we design a two-stream network with the self-attention to extract the modality-specific features from the PAN and MS modalities and apply a cross-attention module to merge the spectral and spatial features. The pan-sharpened image is produced from the enhanced fused features. Extensive experiments on GaoFen-2 and WorldView-3 images demonstrate that our Transformer based model achieves impressive results and outperforms many existing CNN based methods, which shows the great potential of introducing Transformer to the pan-sharpening task. Copyright © 2022, The Authors. All rights reserved.

关键词： Remote sensing

CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Kanglei Li, Junlin Cai, Ruizhi Wang, Liyuan Zhang, Xingxing Liang, Xiaohui Department of Computer Science and Technology Institute for AI BNRist Center Tsinghua-Bosch Joint ML Center THBI Lab Tsinghua University China Zhongguancun Laboratory China State Key Laboratory of Virtual Reality Technology and Systems Beihang University China China Three Gorges University China

Action Quality Assessment (AQA) is pivotal for quantifying actions across domains like sports and medical care. Existing methods often rely on pre-trained backbones from large-scale action recognition datasets to boost performance on smaller AQA datasets. However, this common strategy yields suboptimal results due to the inherent struggle of these backbones to capture the subtle cues essential for AQA. Moreover, fine-tuning on smaller datasets risks overfitting. To address these issues, we propose Coarse-to-Fine Instruction Alignment (CoFInAl). Inspired by recent advances in large language model tuning, CoFInAl aligns AQA with broader pre-trained tasks by reformulating it as a coarse-to-fine classification task. Initially, it learns grade prototypes for coarse assessment and then utilizes fixed sub-grade prototypes for fine-grained assessment. This hierarchical approach mirrors the judging process, enhancing interpretability within the AQA framework. Experimental results on two long-term AQA datasets demonstrate CoFInAl achieves state-of-the-art performance with significant correlation gains of 5.49% and 3.55% on Rhythmic Gymnastics and Fis-V, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Large datasets

Simulating the Dilution of Sulfuric Acid on Mixed reality Platform 8

学校读者我要写书评

暂无评论

Simulating the Dilution of Sulfuric Acid on Mixed Reality Pl...

8th International Conference on virtual reality, ICVR 2022

作者： Pan, Zhipeng Miao, Jinda Cai, Ning Luo, Tianren Zhang, Mingmin Pan, Zhigeng Research Institute of Virtual Reality and Intelligent Systems Hangzhou Normal University Hangzhou China Zhejiang University College of Computer Science and Technology Hangzhou China Institute of Software Chinese Academy of Sciences State Key Laboratory of Computer Science and Beijing Key Lab of Human-Computer Interaction Beijing China Nanjing University of Information Science and Technology School of Artificial Intelligence Nanjing China

ISBN: (数字)9781665479110

ISBN: (纸本)9781665479110

Augmented reality technology has been widely used in experimental education. Augmented reality provides virtual-real integration, real-Time interaction and three-dimensional immersion, which provides a new development direction for simulating the teaching environment and promoting learning interaction. We have developed an MR experiment of diluting concentrated sulfuric acid, which helps students learn experimental manipulations and scientific concepts before conducting real chemical experiments. virtual experiments can avoid the risks of real chemical experiments and reduce the waste of chemical materials. At the same time, we correctly render the occlusion relationship between the hand, the beaker and the virtual liquid, providing a realistic experimental effect. The tracking of multiple cameras allows students to interact more naturally. We compared the availability and students' attitudes of three virtual experiments about diluting concentrated sulfuric acid. The results show that the usability of the MR experimental system reaches the level of user satisfaction. The realistic visual effects and natural interaction method of the MR experiment have been recognized by the students. © 2022 IEEE.

关键词： Students

Denoising Diffusion Autoencoders are Unified Self-supervised Learners

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xiang, Weilai Yang, Hongyu Huang, Di Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Institute of Artificial Intelligence Beihang University Beijing China

Inspired by recent advances in diffusion models, which are reminiscent of denoising autoencoders, we investigate whether they can acquire discriminative representations for classification via generative pre-training. This paper shows that the networks in diffusion models, namely denoising diffusion autoencoders (DDAE), are unified self-supervised learners: by pre-training on unconditional image generation, DDAE has already learned strongly linear-separable representations within its intermediate layers without auxiliary encoders, thus making diffusion pre-training emerge as a general approach for generative-and-discriminative dual learning. To validate this, we conduct linear probe and fine-tuning evaluations. Our diffusion-based approach achieves 95.9% and 50.0% linear evaluation accuracies on CIFAR-10 and Tiny-ImageNet, respectively, and is comparable to contrastive learning and masked autoencoders for the first time. Transfer learning from ImageNet also confirms the suitability of DDAE for Vision Transformers, suggesting the potential to scale DDAEs as unified foundation models. Code is available at ***/FutureXiang/ddae. Copyright © 2023, The Authors. All rights reserved.

关键词： Diffusion

An Empirical Study on Multi-Domain Robust Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Yajie Ge, Pu Liu, Qingjie Fan, Shichao Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

How to effectively leverage the plentiful existing datasets to train a robust and high-performance model is of great significance for many practical applications. However, a model trained on a naive merge of different datasets tends to obtain poor performance due to annotation conflicts and domain divergence. In this paper, we attempt to train a unified model that is expected to perform well across domains on several popularity segmentation datasets. We conduct a detailed analysis of the impact on model generalization from three aspects of data augmentation, training strategies, and model capacity. Based on the analysis, we propose a robust solution that is able to improve model generalization across domains. Our solution ranks 2nd on RVC 2022 semantic segmentation task, with a dataset only 1/3 size of the 1st model used. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

An IoMT Based Epileptic Seizure Predictor Using Dual-Path Temporal-Spectral Encoded Spatial Dynamic Graph Convolution Network

学校读者我要写书评

暂无评论

An IoMT Based Epileptic Seizure Predictor Using Dual-Path Te...

Industrial Automation, robotics and Control Engineering (IARCE), International Conference on

作者： Weidong Yan Mingyi Sun Yang Li Department of Automation Science and Electrical Engineering Beihang University Beijing China Department of Automation Science and Electrical Engineering Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

ISBN: (数字)9798350380323

ISBN: (纸本)9798350380330

Epilepsy is a neurological disorder characterized by recurrent and uncontrolled seizures, severely impacting the safety of patients' lives. It is a challenging task to accurately predict seizures before its occurrence, and timely alarm patients to take appropriate measures to reduce the consequence of seizures. This work proposes an accurate and smart seizure warning predictor, named Seiz-Predictor, which is designed on the basis of the Internet of Medical Thing (IoMT) framework and constructed with a seizure prediction algorithm coupled with a mobile warning application. The Seiz-Predictor employs a dual-path temporal-spectral encoded spatial dynamic graph convolution network (DPTSE-SDGCNet) to enhance seizure prediction accuracy. Additionally, a compatible seizure warning mobile application is developed for seizure alarming, location recording, and interacting with cloud-based databases for further reference by doctors. The designed Seiz-Predictor offers several key benefits, including (1) We propose a novel lightweight network structure more suitable for epileptic seizure warning predictors, achieving more accurate predicting and shorter identification time in the public dataset. (2) A seizure warning mobile application is developed for cloud-based database connectivity, enabling computation of patient epileptic states for doctoral reference. Experimental results on the public CHB-MIT dataset demonstrate that the sensitivity of 96.1% and a false prediction rate of 0.086/h, outperforming the most recent investigations.

关键词： Cloud computing Accuracy Sensitivity Convolution Databases Service robots Epilepsy Internet of Medical Things Mobile applications Safety