检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： He, Zhentao Xia, Changqun Qiao, Shengye Li, Jia State Key Laboratory of Virtual Reality Technology and Systems SCSE Beihang University Beijing China Pengcheng Laboratory Shenzhen China

ISBN: (纸本)9798400706868

Camouflaged instance segmentation (CIS) aims to detect and segment objects blending with their surroundings. While existing CIS methods rely heavily on fully-supervised training with massive precisely annotated data, consuming considerable annotation efforts yet struggling to segment highly camouflaged objects accurately. Despite their visual similarity to the background, camouflaged objects differ semantically. Since text associated with images offers explicit semantic cues to underscore this difference, we propose a novel approach: the first Text-Prompt based weakly-supervised camouflaged instance segmentation method named TPNet, leveraging semantic distinctions for effective segmentation. TPNet operates in two stages: pseudo mask generation and a self-training process. In the first stage, we align text prompts with images using a language-image model to obtain region proposals containing camouflaged instances. A Semantic-Spatial Iterative Fusion module is designed to assimilate spatial information with semantic insights, iteratively refining pseudo mask. In the second stage, Graduated Camouflage Learning, a self-training strategy, sequences training from simple to complex images based on camouflage levels, facilitating an effective learning gradient. Through the collaboration of the dual phases, our method offers a comprehensive experiment on two common benchmark and demonstrates a significant advancement, delivering a novel solution that bridges the gap between weak-supervised and high camouflaged instance segmentation. © 2024 Owner/Author.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Conditional Diffusion Model for 3D Human Pose Estimation 4

A Conditional Diffusion Model for 3D Human Pose Estimation

引用

4th International Conference on Consumer Electronics and Computer Engineering, ICCECE 2024

作者： Chen, Zhangmeng Dai, Ju Pan, Junjun Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing China Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9798350384062

Monocular 3D human pose estimation is a highly challenging task due to inherent depth ambiguity and occlusion. In response to these challenges, many previous works have utilized temporal information to enhance the richness of information. However, such methods can only derive a specific 3D pose from a single image, which fails to address ambiguity. Fortunately, denoising diffusion probabilistic models have recently achieved success in various computer vision tasks (e.g., generating images and image segmentation). Diffusion-based methods produce a set of possible result for each image. Inspired by this, we explore a novel Conditional Diffusion-based 3D human Pose estimation framework (CDiffPose) that formulates 3D human pose estimation as a 2D keypoints-guided 3D pose synthesis problem. We utilize a pre-trained model to represent 2D keypoints information as conditioning information. Subsequently, we inject the conditional information into the denoising model. Our denoising model (Denoiser) adopts a cascaded approach involving GCN and Transformers. Finally, the model generates multiple 3D candidates poses for a single 2D keypoint to alleviate the inherent depth ambiguity. Extensive experiments are conducted on Human3.6M benchmark, our proposed method demonstrates competitive performance. © 2024 IEEE.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Robust and efficient edge-based visual odometry

引用

Computational Visual Media 2022年第3期8卷 467-481页

作者： Feihu Yan Zhaoxin Li Zhong Zhou State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China Institute of Computing Technology Chinese Academy ofSciencesBeijing 100190China

Visual odometry,which aims to estimate relative camera motion between sequential video frames,has been widely used in the fields of augmented reality,virtual reality,and autonomous ***,it is still quite challenging for stateof-the-art approaches to handle low-texture *** this paper,we propose a robust and efficient visual odometry algorithm that directly utilizes edge pixels to track camera *** contrast to direct methods,we choose reprojection error to construct the optimization energy,which can effectively cope with illumination *** distance transform map built upon edge detection for each frame is used to improve tracking efficiency.A novel weighted edge alignment method together with sliding window optimization is proposed to further improve the *** on public datasets show that the method is comparable to stateof-the-art methods in terms of tracking accuracy,while being faster and more robust.

关键词： visual odometry(VO) edge structure distance transform low-texture

来源：评论

学校读者我要写书评

暂无评论

Identification of Gingival Inflammation Surface Image Features Using Intraoral Scanning and Deep Learning

引用

International Dental Journal 2025年第3期75卷 2104-2114页

作者： Li, Wei Li, Linlin Xu, Wenchong Guo, Yuting Xu, Min Huang, Shengyuan Dai, Dong Lu, Chang Li, Shuai Lin, Jiang Department of Stomatology Beijing Tongren Hospital Capital Medical University Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China

Introduction and aim: The assessment of gingival inflammation surface features mainly depends on subjective judgment and lacks quantifiable and reproducible indicators. Therefore, it is a need to acquire objective identification information for accurate monitoring and diagnosis of gingival inflammation. This study aims to develop an automated method combining intraoral scanning (IOS) and deep learning algorithms to identify the surface features of gingival inflammation and evaluate its accuracy and correlation with clinical indicators. Methods: The study included the periodontal probing data and intraoral scan images of 120 patients with periodontitis. The deep learning model GC-U-Net was used to automatically segment and identify the gingival inflammation regions. The performance of the model was evaluated by the Dice coefficient (Dice), intersection over union (IoU), and pixel accuracy (PA), and the correlation between the identification performance and the periodontal examination index was analysed. Results: The GC-U-Net model showed high recognition accuracy, with a Dice of 77.8%, an IoU of 65.4%, and a PA of 93.7%. This model demonstrated a strong positive correlation with the sulcus bleeding index (SBI;r = 0.836, P < .001), a moderately strong positive correlation with the bleeding index (BI;r = 0.618, P < .001), and a negative correlation with the probe depth (PD;r = - 0.425, P < .001). Conclusion: The study has successfully developed an automatic identification method for surface characteristics of gingival inflammation based on deep learning and IOS technology, providing a standardised and automated auxiliary tool for clinical gingival inflammation examination with high accuracy and significant correlation with clinical indicators. Clinical Relevance: This method can reduce subjective judgment in the clinical assessment of gingival inflammation, improve the consistency and reliability of identification, and play an important auxiliary role in clinical diagn

关键词： Artificial intelligence Deep learning Gingival inflammation Intraoral scanning Periodontitis

来源：评论

学校读者我要写书评

暂无评论

Subthreshold Depression Recognition and Correlation Study from Pulse Condition via Stacking Ensemble Algorithm 1st

Subthreshold Depression Recognition and Correlation Study f...

引用

1st International Conference on Extended reality, ICXR 2024

作者： Jiang, Han Li, Ming Gao, Yang Li, Peiru State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9789819636785

Subthreshold depression, a transition state to depression, seriously hinders the early diagnosis of depression. Current studies mostly use heterogeneous definitions of subthreshold depression, making the results of such meta-analyses questionable. Therefore, it is of vital significance to develop an objective method for the diagnosis of subthreshold depression based on objective criteria. In traditional Chinese medicine (TCM), symptoms similar to subthreshold depression have been extensively explored. However, diagnostic methods in TCM still depend heavily on the experience of doctors and lack integration with modern diagnostic techniques, which makes it challenging to explain the pathogenesis of subthreshold depression. Consequently, we propose an explainable framework, based on a stacking ensemble algorithm, for subthreshold depression recognition from biomarkers in the pulse waveform and concepts of pulse in TCM. In this method, Naive Bayes, Random Forest, Extremely Randomized Trees, Categorical Boosting and Logistic Regression are chosen as basic learners, and XGBoost is selected as the meta-classifier. Based on the five-fold cross-validation method, grid search method and repetition of training, the stacking ensemble model shows superiority on most performance evaluation metrics including AUC, F1 scores, MCC, precision and sensitivity. Besides, by analyzing the Adjusted Odds Ratio of features in the pulse waveform, we obtained four features that have a high correlation with the occurrence of subthreshold depression and derived physiological changes in patients with subthreshold depression based on their physiological significance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Reborn of the White Bone Demon: Role-Playing Game Design Using Generative AI in XR 24

Reborn of the White Bone Demon: Role-Playing Game Design Usi...

引用

2024 SIGGRAPH Asia 2024 Posters, SA 2024

作者： Liang, Xiaozhan Wang, Yu Yan, Fengyi Ouyang, Zehong Hu, Yong Luo, Siyu Beihang University Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Tsinghua University China

ISBN: (纸本)9798400711381

This paper explores the application of Generative Artificial Intelligence (GenAI) techniques to the design of Role Playing Games (RPGs) in Extended reality (XR) environments. We developed the game Reborn of the White Bone Demon, which utilizes AI speech emotion recognition technology to generate story lines and game assets in real-time based on the player's conversations with NPCs, enhancing the player's immersion and personalized experience, demonstrating the potential of GenAI in enhancing the XR gaming experience. © 2024 Copyright held by the owner/author(s).

关键词： Game design

来源：评论

学校读者我要写书评

暂无评论

Adaptive multiscale microscope with fast zooming,extended working distance,and large field of view

引用

Light(Advanced Manufacturing) 2024年第1期5卷 60-72页

作者： Yi Zheng Xin Wang Zhao Jiang Jinbo Xu Rongying Yuan Youran Zhao Haoran Zhang Chao Liu Qionghua Wang School of Instrumentation and Optoelectronic Engineering Beihang UniversityBeijing 100191China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China

The field-of-view(FOV),depth of field,and resolution of conventional microscopes are constrained by each other;therefore,a zoom function is *** zoom methods lose real-time performance and have limited information throughput,severely limiting their application,especially in three-dimensional dynamic imaging and large-amount or large-size sample ***,an adaptive multiscale(AMS)imaging mechanism combining the benefits of liquid lenses and multiscale imaging techniques is proposed to realize the functions of fast zooming,wide working distance(WD)range and large FOV on a self-developed AMS *** design principles were ***,a nonuniform-distortion-correction algorithm and a composite patching algorithm were designed to improve image *** continuous tunable magnification range of the AMS microscope is from 9×to 18×,with the corresponding FOV diameters and resolution ranging from 2.31 to 0.98 mm and from 161 to 287 line-pairs/mm,*** extended WD range is 0.8 mm and the zoom response time is 38 *** demonstrated the advantages of the proposed microscope in pathological sample scanning,thick-sample imaging,microfluidic process monitoring,and the observation of living *** proposed microscope is the first step towards zoom multiscale imaging technology and is expected to be applied in life sciences,medical diagnosis,and industrial detection.

关键词： Microscope Multiscale Liquid lens Zoom

来源：评论

学校读者我要写书评

暂无评论

Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning 38

Transforming Vision Transformer: Towards Efficient Multi-Tas...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Zhong, Hanwen Chen, Jiaxin Zhang, Yutong Huang, Di Wang, Yunhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University China School of Computer Science and Engineering Beihang University Beijing China

Multi-Task Learning (MTL) for Vision Transformer aims at enhancing the model capability by tackling multiple tasks simultaneously. Most recent works have predominantly focused on designing Mixture-of-Experts (MoE) structures and integrating Low-Rank Adaptation (LoRA) to efficiently perform multi-task learning. However, their rigid combination hampers both the optimization of MoE and the effectiveness of reparameterization of LoRA, leading to sub-optimal performance and low inference speed. In this work, we propose a novel approach dubbed Efficient Multi-Task Learning (EMTAL) by transforming a pre-trained Vision Transformer into an efficient multi-task learner during training, and reparameterizing the learned structure for efficient inference. Specifically, we firstly develop the MoEfied LoRA structure, which decomposes the pre-trained Transformer into a low-rank MoE structure and employ LoRA to fine-tune the parameters. Subsequently, we take into account the intrinsic asynchronous nature of multi-task learning and devise a learning Quality Retaining (QR) optimization mechanism, by leveraging the historical high-quality class logits to prevent a well-trained task from performance degradation. Finally, we design a router fading strategy to integrate the learned parameters into the original Transformer, archiving efficient inference. Extensive experiments on public benchmarks demonstrate the superiority of our method, compared to the state-of-the-art multi-task learning approaches. The project page is available at https://***/Yewen1486/EMTAL. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Divide and Conquer Solution for Long-term Video Salient Object Detection

引用

Machine Intelligence Research 2024年第4期21卷 684-703页

作者： Yun-Xiao Li Cheng-Li-Zhao Chen Shuai Li Ai-Min Hao Hong Qin State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China College of Computer Science and Technology China University of Petroleum(East China)Qingdao 266580China Department of Computer Science Stony Brook UniversityNew York 11794USA

Recently,a new research trend in our video salient object detection(VSOD)research community has focused on enhancing the detection results via model self-fine-tuning using sparsely mined high-quality keyframes from the given *** such a learning scheme is generally effective,it has a critical limitation,i.e.,the model learned on sparse frames only possesses weak generalization *** situation could become worse on“long”videos since they tend to have intensive scene ***,in such videos,the keyframe information from a longer time span is less relevant to the previous,which could also cause learning conflict and deteriorate the model ***,the learning scheme is usually incapable of handling complex pattern *** solve this problem,we propose a divide-and-conquer framework,which can convert a complex problem domain into multiple simple ***,we devise a novel background consistency analysis(BCA)which effectively divides the mined frames into disjoint *** for each group,we assign an individual deep model on it to capture its key attribute during the fine-tuning *** the testing phase,we design a model-matching strategy,which could dynamically select the best-matched model from those fine-tuned ones to handle the given testing *** experiments show that our method can adapt severe background appearance variation coupling with object movement and obtain robust saliency detection compared with the previous scheme and the state-of-the-art methods.

关键词： Video salient object detection background consistency analysis weakly supervised learning long-term information background shift.

来源：评论

学校读者我要写书评

暂无评论

Multi-task learning andjoint refinement between camera localization and object detection

引用

Computational Visual Media 2024年第5期10卷 993-1011页

作者： Junyi Wang Yue Qi State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Peng Cheng Laboratory Shenzhen 518052China Qingdao Research Institute of Beihang University Qingdao 266104China School of Computer Science and Technology Shandong UniversityQingdaoChina

Visual localization and object detection both play important roles in various *** many indoor application scenarios where some detected objects have fixed positions,the two techniques work closely ***,few researchers consider these two tasks simultaneously,because of a lack of datasets and the little attention paid to such *** this paper,we explore multi-task network design and joint refinement of detection and *** address the dataset problem,we construct a medium indoor scene of an aviation exhibition hall through a semi-automatic *** dataset provides localization and detection information,and is publicly available at https://***/drive/folders/1U28zk0N4_I0db zkqyIAK1A15k9oUKOjI?usp=sharing for benchmarking localization and object detection *** this dataset,we have designed a multi-task network,JLDNet,based on YOLO v3,that outputs a target point cloud and object bounding *** dynamic environments,the detection branch also promotes the perception of *** includes image feature learning,point feature learning,feature fusion,detection construction,and point cloud ***,object-level bundle adjustment is used to further improve localization and detection *** test JLDNet and compare it to other methods,we have conducted experiments on 7 static scenes,our constructed dataset,and the dynamic TUM RGB-D and Bonn *** results show state-of-the-art accuracy for both tasks,and the benefit of jointly working on both tasks is demonstrated.

关键词： visual localization object detection joint optimization multi-task learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：