检索结果-内蒙古大学图书馆

Joint self-supervised and reference-guided learning for depth inpainting

Computational Visual Media 2022年第4期8卷 597-612页

作者： Heng Wu Kui Fu Yifan Zhao Haokun Song Jia Li State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Depth information can benefit various computer vision tasks on both images and ***,depth maps may suffer from invalid values in many pixels,and also large *** improve such data,we propose a joint self-supervised and reference-guided learning approach for depth *** the self-supervised learning strategy,we introduce an improved spatial convolutional sparse coding module in which total variation regularization is employed to enhance the structural information while preserving edge *** module alternately learns a convolutional dictionary and sparse coding from a corrupted depth ***,both the learned convolutional dictionary and sparse coding are convolved to yield an initial depth map,which is effectively smoothed using local contextual *** reference-guided learning part is inspired by the fact that adjacent pixels with close colors in the RGB image tend to have similar depth *** thus construct a hierarchical joint bilateral filter module using the corresponding color image to fill in large *** summary,our approach integrates a convolutional sparse coding module to preserve local contextual information and a hierarchical joint bilateral filter module for filling using specific adjacent *** results show that the proposed approach works well for both invalid value restoration and large hole inpainting.

关键词： depth inpainting self-supervised learning reference-guided learning

来源：评论

学校读者我要写书评

暂无评论

From animal collective behaviors to swarm robotic cooperation

引用

National science Review 2023年第5期10卷 82-99页

作者： Haibin Duan Mengzhen Huo Yanming Fan State Key Laboratory of Virtual Reality Technology and Systems School of Automation Science and Electrical EngineeringBeihang University Virtual Reality Fundamental Research Laboratory Department of Mathematics and TheoriesPeng Cheng Laboratory AVIC Shenyang Aircraft Design and Research Institute

The collective behaviors of animals,from schooling fish to packing wolves and flocking birds,display plenty of fascinating phenomena that result from simple interaction rules among *** emergent intelligent properties of the animal collective behaviors,such as self-organization,robustness,adaptability and expansibility,have inspired the design of autonomous unmanned swarm *** article reviews several typical natural collective behaviors,introduces the origin and connotation of swarm intelligence,and gives the application case of animal collective *** this basis,the article focuses on the forefront of progress and bionic achievements of aerial,ground and marine robotics swarms,illustrating the mapping relationship from biological cooperative mechanisms to cooperative unmanned cluster ***,considering the significance of the coexisting-cooperative-cognitive human-machine system,the key technologies to be solved are given as the reference directions for the subsequent exploration.

关键词： collective behaviors swarm intelligence cooperative robotics swarm human-machine system

来源：评论

学校读者我要写书评

暂无评论

Offline Reinforcement Learning with Constrained Hybrid Action Implicit Representation Towards Wargaming Decision-Making

引用

Tsinghua science and technology 2024年第5期29卷 1422-1440页

作者： Liwei Dong Ni Li Guanghong Gong Xin Lin School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191China School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191ChinaState Key Laboratory of Virtual Reality Technology and SystemsBeihang UniversityBeijing 100191Chinaand also with Zhongguancun LaboratoryBeijing 100191China School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191Chinaand also with State Key Laboratory of Virtual Reality Technology and SystemsBeihang UniversityBeijing 100191China

Reinforcement Learning(RL)has emerged as a promising data-driven solution for wargaming ***,two domain challenges still exist:(1)dealing with discrete-continuous hybrid wargaming control and(2)accelerating RL deployment with rich offline *** RL methods fail to handle these two issues simultaneously,thereby we propose a novel offline RL method targeting hybrid action space.A new constrained action representation technique is developed to build a bidirectional mapping between the original hybrid action space and a latent space in a semantically consistent *** allows learning a continuous latent policy with offline RL with better exploration feasibility and scalability and reconstructing it back to a needed hybrid ***,a novel offline RL optimization objective with adaptively adjusted constraints is designed to balance the alleviation and generalization of out-of-distribution *** method demonstrates superior performance and generality across different tasks,particularly in typical realistic wargaming scenarios.

关键词： offline Reinforcement Learning(RL) wargaming decision-making hybrid action space

来源：评论

学校读者我要写书评

暂无评论

Drogue detection for autonomous aerial refueling via hybrid pigeon-inspired optimized color opponent and saliency aggregation

引用

Chinese Journal of Aeronautics 2024年第5期37卷 27-38页

作者： Tongyan WU Haibin DUAN Yanming FAN State Key Laboratory of Virtual Reality Technology and Systems School of Automation Science and Electrical EngineeringBeihang UniversityBeijing 100083China Virtual Reality Fundamental Research Laboratory Department of Mathematics and TheoriesPeng Cheng LaboratoryShenzhen 518000China AVIC Shenyang Aircraft Design and Research Institute Shenyang 110035China

Drogue detection is one of the challenging tasks in autonomous aerial refueling due to the requirement for accuracy and *** detection based on image intrinsic cues can achieve fast detection,but with poor *** studies reveal that optimization-based methods provide accurate and quick solutions for saliency *** paper presents a hybrid pigeon-inspired optimization method,the optimized color opponent,that aims to adjust the weight of color opponent channels to detect the drogue *** can optimize the weights in the selected aerial refueling scene offline,and the results are applied for drogue detection in the scene.A novel algorithm aggregated by the optimized color opponent and robust background detection is presented to provide better precision and *** results on benchmark datasets and aerial refueling images show that the proposed method successfully extracts the saliency region or drogue and exhibits superior performance against the other saliency detection methods with intrinsic *** algorithm designed in this paper is competent for the drogue detection task of autonomous aerial refueling.

关键词： Autonomous aerial refueling Drones Hybrid pigeon-inspired optimization Color opponent Saliency detection Saliency aggregation

来源：评论

学校读者我要写书评

暂无评论

D-scheduler:A scheduler in time-triggered distributed system through decoupling dependencies between tasks and messages

引用

science China(Technological sciences) 2024年第1期67卷 183-196页

作者： YANG TingTing ZHANG YuQi YUE FengLai WUNIRI QiQiGe TONG Chao School of Computer Science&Engineering Beihang UniversityBeijing 100191China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China National Innovation Center of Intelligent and Connected Vehicles Beijing 100176China

Time-triggered architecture,as a mainstream design of the distributed real-time system,has been successfully applied in the aerospace,automotive and mechanical ***,time-triggered scheduling is a challenging NP-hard *** are few studies that could quickly solve the scheduling problem of large distributed time-triggered *** solve this problem,a communication affinity parameter is defined in this paper to describe the degree of bias of the shaper task towards sending or receiving *** on this,an innovative task-message decoupling model named D-scheduler is built to reduce the computation complexity of the scheduling problem in large-scale ***,we provide mathematical proof that our model is a convex optimization that is easy to solve with existing computational *** experiments substantiate the efficacy of the *** dramatically reduces the scheduling complexity of large-scale real-time systems with a small loss of solving space compared to the federal scheduler.

关键词： time-triggered architecture time-triggered scheduling communication affinity parameter task-message decoupling model

来源：评论

学校读者我要写书评

暂无评论

A survey for light field super-resolution

引用

High-Confidence Computing 2024年第1期4卷 118-129页

作者： Mingyuan Zhao Hao Sheng Da Yang Sizhe Wang Ruixuan Cong Zhenglong Cui Rongshan Chen Tun Wang Shuai Wang Yang Huang Jiahao Shen State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Key Laboratory of Data Science and Intelligent Computing International Innovation InstituteBeihang UniversityHangzhou 311115China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Compared to 2D imaging data,the 4D light field(LF)data retains richer scene’s structure information,which can significantly improve the computer’s perception capability,including depth estimation,semantic segmentation,and LF ***,there is a contradiction between spatial and angular resolution during the LF image acquisition *** overcome the above problem,researchers have gradually focused on the light field super-resolution(LFSR).In the traditional solutions,researchers achieved the LFSR based on various optimization frameworks,such as Bayesian and Gaussian *** learning-based methods are more popular than conventional methods because they have better performance and more robust generalization *** this paper,the present approach can mainly divided into conventional methods and deep learning-based *** discuss these two branches in light field spatial super-resolution(LFSSR),light field angular super-resolution(LFASR),and light field spatial and angular super-resolution(LFSASR),***,this paper also introduces the primary public datasets and analyzes the performance of the prevalent approaches on these ***,we discuss the potential innovations of the LFSR to propose the progress of our research field.

关键词： Light field super-resolution Convolutional neural network Transformer Sub-aperture image Epipolar-plane image

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

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

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

3D scene graph prediction from point clouds

引用

virtual reality & Intelligent Hardware 2022年第1期4卷 76-88页

作者： Fanfan WU Feihu YAN Weimin SHI Zhong ZHOU State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Background In this study,we propose a novel 3D scene graph prediction approach for scene understanding from point *** It can automatically organize the entities of a scene in a graph,where objects are nodes and their relationships are modeled as *** specifically,we employ the DGCNN to capture the features of objects and their relationships in the scene.A Graph Attention Network(GAT)is introduced to exploit latent features obtained from the initial estimation to further refine the object arrangement in the graph structure.A one loss function modified from cross entropy with a variable weight is proposed to solve the multi-category problem in the prediction of object and *** Experiments reveal that the proposed approach performs favorably against the state-of-the-art methods in terms of predicate classification and relationship prediction and achieves comparable performance on object classification *** The 3D scene graph prediction approach can form an abstract description of the scene space from point clouds.

关键词： Scene understanding 3D scene graph Point cloud DGCNN GAT

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：