检索结果-内蒙古大学图书馆

C2P-Net: Comprehensive Depth Map to Planar Depth Conversion for Room Layout Estimation

IEEE Transactions on Pattern Analysis and machine intelligence 2025年 PP卷 PP页

作者： Zhang, Weidong Zhou, Mengjie Cheng, Jiyu Liu, Ying Zhang, Wei Xi'an University of Posts & Telecommunications School of Communications and Information Engineering China Xi'an Key Laboratory of Image Processing Technology and Applications for Public Security China Shandong University School of Control Science and Engineering China Ministry of Education Key Laboratory of Machine Intelligence and System Control China

Room layout estimation seeks to infer the overall spatial configuration of indoor scenes using perspective or panoramic images. As the layout is determined by the dominant indoor planes, this problem inherently requires the reconstruction of these planes. Some studies reconstruct indoor planes from perspective images by learning pixel-level or instance-level plane parameters. However, directly learning these parameters has the problems of susceptibility to occlusions and position dependency. In this paper, we introduce the Comprehensive depth map to Planar depth (C2P) conversion, which reformulates planar depth reconstruction into the prediction of a comprehensive depth map and planar visibility confidence. Based on the parametric representation of planar depth we propose, the C2P conversion is applicable to both panoramic and perspective images. Accordingly, we present an effective framework for room layout estimation that jointly learns the comprehensive depth map and planar visibility confidence. Due to the differentiability of the C2P conversion, our network autonomously learns planar visibility confidence by constraining the estimated plane parameters and reconstructed planar depth map. We further propose a novel approach for 3D layout generation through sequential planar depth map integration. Experimental results demonstrate the superiority of our method across all evaluated panoramic and perspective datasets. © 1979-2012 IEEE.

关键词： Image-Text Matching Medical Report Generation Sample-graph Consistency Self-boosting framework

来源：评论

学校读者我要写书评

暂无评论

SIEVL-Track: Exploring Semantic Information Enhancement for Visual-Language Object Tracking

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Li, Ning Zhong, Bineng Liang, Qihua Mo, Zhiyi Nong, Jian Song, Shuxiang Ministry of Education Guangxi Normal University Key Laboratory of Education Blockchain and Intelligent Technology Guilin541004 China Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining and Security Guilin541004 China Wuzhou University Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou543002 China

With the assistance of language descriptions, Visual-Language (VL) object tracking can obtain more accurate semantic information compared to traditional Visual-Only object tracking. However, the ability of current VL trackers to obtain target semantic information has not been fully developed due to limitations such as wasted modeling capabilities and insufficient utilization of historical temporal information. On the one hand, the modeling output from Transformer shallow encoders often does not directly participate in the prediction of tracking results, resulting in a certain degree of model capability waste. On the other hand, the semantic information of historical tracking results has also not been fully utilized in the tracking process, resulting in a certain degree of lack of semantic assistance capability. Therefore, we propose a novel hierarchical multi-stage VL tracker called SIEVL-Track to enhance target semantic information. Specifically, we first design a multi-stage visual language tracking framework for modeling multi-scale semantic information in Visual-Language tracking pipeline. Secondly, we propose a selective deep and shallow semantic information fusion module (S-DSFM) that explicitly integrates shallow output features into deep output features, so to reduce the waste of modeling capabilities and obtain more high-frequency semantic information related to the target. Finally, we design a temporal cue modeling module based on linguistic classification and multi-frame historical information(MHLS-TCM), with the aim of more comprehensive utilization of historical temporal semantic information. Benefit from the above designs, our VL tracker can obtain stronger target semantic information. Competitive performance from extensive experimental results on five popular vision-language tracking benchmarks, including LaSOT, OTB99-Lang, WebUAV-3M, LaSOText and TNL2K, have demonstrated the superiority and effectiveness of our SIEVL-Track. © 1991-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Approximately Invertible Neural Network for Learned Image Compression

引用

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society 2025年 PP卷 PP页

作者： Yanbo Gao Shuai Li Meng Fu Chong Lv Zhiyuan Yang Xun Cai Hui Yuan Mao Ye School of Software Shandong University Jinan China Shandong University-WeiHai Research Institute of Industrial Technology Shandong University Weihai China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China University of Electronic Science and Technology of China Chengdu Sichuan China

Learned image compression has attracted considerable interests in recent years. An analysis transform and a synthesis transform, which can be regarded as coupled transforms, are used to encode an image to latent feature and decode the feature after quantization to reconstruct the image. Inspired by the success of invertible neural networks in generative modeling, invertible modules can be used to construct the coupled analysis and synthesis transforms. Considering the noise introduced in the feature quantization invalidates the invertible process, this paper proposes an Approximately Invertible Neural Network (A-INN) framework for learned image compression. It formulates the rate-distortion optimization in lossy image compression when using INN with quantization, which differentiates from using INN for generative modelling. Generally speaking, A-INN can be used as the theoretical foundation for any INN based lossy compression method. Based on this formulation, A-INN with a progressive denoising module (PDM) is developed to effectively reduce the quantization noise in the decoding. Moreover, a Cascaded Feature Recovery Module (CFRM) is designed to learn high-dimensional feature recovery from low-dimensional ones to further reduce the noise in feature channel compression. In addition, a Frequency-enhanced Decomposition and Synthesis Module (FDSM) is developed by explicitly enhancing the high-frequency components in an image to address the loss of highfrequency information inherent in neural network based image compression, thereby enhancing the reconstructed image quality. Extensive experiments demonstrate that the proposed A-INN framework achieves better or comparable compression efficiency than the conventional image compression approach and state-of-the-art learned image compression methods.

关键词： Image coding Transforms Decoding Neural networks Quantization (signal) Image reconstruction Noise Entropy Optimization Transform coding

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Guided Diffusion Model for Camouflaged Object Detection

引用

IEEE Transactions on Multimedia 2025年

作者： Yang, Jinsheng Zhong, Bineng Liang, Qihua Mo, Zhiyi Zhang, Shengping Song, Shuxiang Guangxi Normal University Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guilin541004 China Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining & Security China Wuzhou University Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou543002 China Harbin Institute of Technology School of Computer Science and Technology Weihai264209 China

Recently, diffusion models have significantly improved the performance of Camouflaged Object Detection (COD) by adding noise to a mask and iteratively denoising it to match the target distributions. Due to the direct extraction of features from noisy masks and the lack of conditional constraints on a prediction area, the diffusion model may deviate from a correct prediction range and produces mispredictions in regions with high uncertainty. To address this issue, we propose an uncertainty-guided diffusion model (UGDNet) for COD, which explicitly quantifies uncertainty and integrates it as an anchor condition into the diffusion models to provide an initialization of the diffusion regions. The core idea is first to utilize a probability representation and transformer to explicitly model uncertainty, aiming to identify areas where a model may generate overconfident mispredictions. Then, we use the uncertainty as an anchor condition to provide a reference prediction range for the diffusion model, guiding each step of the diffusion process. Furthermore, we use uncertainty to guide feature aggregation, prompting the model to pay extra attention to the semantic features of regions with high uncertainty to refine the segmentation results further. The experimental results indicate that our proposed UGDNet achieves higher accuracy than existing state-of-the-art models on five COD benchmarks, including COD10K, NC4K, CAMO, CHAMELEON, and CDS2K. © 1999-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

TRNet: Two-Tier Recursion Network for Co-Salient Object Detection

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Cong, Runmin Yang, Ning Liu, Hongyu Zhang, Dingwen Huang, Qingming Kwong, Sam Zhang, Wei Shandong University School of Control Science and Engineering Jinan250061 China Ministry of Education Key Laboratory of Machine Intelligence and System Control Jinan250061 China Beijing Jiaotong University Institute of Information Science Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Northwestern Polytechnical University Brain and Artificial Intelligence Laboratory School of Automation Xi'an710129 China University of Chinese Academy of Sciences School of Computer Science and Technology Beijing101408 China Lingnan University Hong Kong

Co-salient object detection (CoSOD) is to find the salient and recurring objects from a series of relevant images, where modeling inter-image relationships plays a crucial role. Different from the commonly used direct learning structure that inputs all the intra-image features into some well-designed modules to represent the inter-image relationship, we resort to adopting a recursive structure for inter-image modeling, and propose a two-tier recursion network (TRNet) to achieve CoSOD in this paper. The two-tier recursive structure of the proposed TRNet is embodied in two stages of inter-image extraction and distribution. On the one hand, considering the task adaptability and inter-image correlation, we design an inter-image exploration with recursive reinforcement module to learn the local and global inter-image correspondences, guaranteeing the validity and discriminativeness of the information in the step-by-step propagation. On the other hand, we design a dynamic recursion distribution module to fully exploit the role of inter-image correspondences in a recursive structure, adaptively assigning common attributes to each individual image through an improved semi-dynamic convolution. Experimental results on five prevailing CoSOD benchmarks demonstrate that our TRNet outperforms other competitors in terms of various evaluation metrics. The code and results of our method are available at https://***/rmcong/TRNetTCSVT2025. © 1991-2012 IEEE.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Intelligent Construction and Analysis of a Complex Network for Determining Risk-Influencing Factors in Ship Self-Sinking Accidents

引用

ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering 2025年第3期11卷

作者： Ma, Jun Wang, Liguang Xu, Luhui Zhao, Jiong Lin, Rui School of Computer Science Xijing Univ. Xi'An Key Laboratory of Human-Machine Integration and Control Technology for Intelligence Xi'an710123 China School of Computer Science Xijing Univ. Xi'an710123 China Xi'An Senke Construction Engineering Co. Xi'an710043 China

One of the most effective methods for analyzing risk-influencing factors (RIFs) in maritime accidents is the complex network approach. However, there is limited research specifically focused on RIFs in ship self-sinking accidents. Moreover, challenges remain in the accurate ontology construction of RIFs based on the data set, intelligent extraction of RIF propagation paths, RIF importance ranking, and robustness analysis of complex networks. To address these issues, an intelligent method is proposed to construct a ship self-sinking accident RIF complex network (SSARIFCN) based on 204 accident reports, yielding 247 nodes and 1,872 edges derived from 488 RIF propagation paths. This approach significantly improves the objectivity and accuracy of RIF identification while enhancing the intelligence level of the information extraction process. The three-weight LeaderRank algorithm is applied for node importance ranking and network robustness analysis, outperforming eight traditional ranking models and five attack algorithms, enhancing the accuracy of key RIF identification. Based on this algorithm, the top five RIFs for ship self-sinking accidents were identified, concluding that "unfit for maritime navigation"is a frequently overlooked key RIF. The experiment validates the method's effectiveness in identifying key RIFs, controlling RIF propagation, and enhancing accident prevention and navigational safety. © 2025 American Society of Civil Engineers.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Behavioral Intervention with Eye-Use Monitoring to Delay Myopia Onset and Progression in Children: A Cluster Randomized Trial

引用

Ophthalmology 2025年第6期132卷 701-712页

作者： Hu, Yuanyuan Yu, Mingkun Han, Xiaotong Congdon, Nathan Wu, Ziyun Liu, Jianping Liu, Zhaolan Huo, Huanhuan Song, Jike He, Mingguang Bi, Hongsheng Affiliated Eye Hospital of Shandong University of Traditional Chinese Medicine Shandong Academy of Eye Disease Prevention and Therapy Shandong Provincial Key Laboratory of Integrated Traditional Chinese and Western Medicine for Prevention and Therapy of Ocular Diseases Shandong Provincial Clinical Medical Research Center of Optometry and Children Visual Impairment Prevention and Control Shandong Engineering Technology Research Center of Visual Intelligence Shandong Institute of Children Health and Myopia Prevention and Control Shandong China Shandong University of Traditional Chinese Medicine Shandong China State Key Laboratory of Ophthalmology Zhongshan Ophthalmic Center SunYat-sen University Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science Guangdong Provincial Clinical Research Center for Ocular Diseases Guangzhou China Centre for Public Health Queen's University Belfast Belfast United Kingdom Ophthalmology and Optometry Medical School Shandong University of Traditional Chinese Medicine Shandong China Affiliated Yongchuan Hospital of Chongqing Medical University Chongqing China Centre for Evidence Based Chinese Medicine Beijing University of Chinese Medicine Beijing China Research Centre for SHARP Vision The Hong Kong Polytechnic University Hong Kong

Purpose: To assess the efficacy of a behavioral intervention using Eye-Use Monitoring technology to delay the onset and progression of myopia in children. Design: A prospective, cluster-randomized, parallel-groups, examiner-masked, clinical trial (Chinese Clinical Trial Registry, ChiCTR2100052101). Participants: A total of 413 children from grades 2 to 4 in Shandong, China, from October 2021 to December 2023 were randomized by class into 3 groups: reminder and feedback (6 classes, 156 children), reminder-only (5 classes, 147 children), and control (3 classes, 110 children). Children with prior myopia control interventions, significant eye conditions, or a history of eye diseases were excluded. Methods: The reminder-only group received simultaneous vibration alerts for prolonged near work, close proximity, head tilt, or inadequate lighting. The reminder and feedback group received these alerts plus behavioral feedback, including praise, rewards, and weekly reports. The control group received no intervention. The intervention lasted 49 weeks, followed by a 49-week observation period without intervention. Main Outcome Measures: The primary outcome was the mean change in cycloplegic spherical equivalent (SE) at 49 weeks. Secondary outcomes included changes in axial length (AL), myopia incidence, rates of rapid myopic shift, participant compliance, and eye-use behaviors. Results: At 49 weeks, changes in SE and AL were least in the reminder and feedback group (SE: 0.52 ± 0.35 diopters [D] vs. 0.59 ± 0.43 D vs. 0.73 ± 0.48 D, AL: 0.30 ± 0.14 mm vs. 0.33 ± 0.16 mm vs. 0.40 ± 0.20 mm, in reminder and feedback group, reminder only group, and control group, respectively, both P < 0.001). Myopia incidence was lowest in the reminder and feedback group (13.3% vs. 21.6% vs. 27.8%, in reminder and feedback group, reminder only group, and control group, respectively, P < 0.05). However, differences diminished by the 98-week follow-up. Conclusions: This study demonstrated that the co

关键词： Children Cluster randomized controlled trials Eye-use behaviors Myopia Spherical equivalent

来源：评论

学校读者我要写书评

暂无评论

Channel and space-based joint rate allocation algorithm

Channel and space-based joint rate allocation algorithm

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Dayong Wang Chao Yuan Yu Sun Xin Lu Hui Guo Frederic Dufaux Ce Zhu Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications China Department of Computer Science University of Central Arkansas Faculty of Computing Engineering and Media (CEM) De Montfort University UK Université Paris-Saclay CNRS CentraleSupélec Laboratoire Des Signaux et Systèmes France School of Information and Communication Engineering University of Electronic Science and Technology of China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Rate control is a critical component for image and video compression Particularly under limited network bandwidth conditions, bitrate control is essential to ensure efficient image transmission by effectively allocation channel resources. In this research, since both Channel and Spatial have relationship with rate allocation, we first propose a joint Channel-wise and Spatial-wise Quantization scheme to determine optimal quantization parameters. Subsequently, we develop a quantization step estimation network to obtain parameters to efficiently allocate rate according to target rate. Experiments demonstrate that our algorithm significantly improve compressed image quality with minimal bitrate distortion and achieve accurate rate control with nearly 3% average bitrate error.

关键词： Image quality Quantization (signal) Image coding Bit rate Signal processing algorithms Estimation Rate-distortion Video compression Resource management Speech processing

来源：评论

学校读者我要写书评

暂无评论

Global Spatial-Temporal Information-based Residual ConvLSTM for Video Space-Time Super-Resolution

引用

IEEE Transactions on Multimedia 2025年

作者： Fu, Congrui Yuan, Hui Jiang, Shiqi Zhang, Guanghui Shen, Liquan Hamzaoui, Raouf Center of Experimental Teaching China Shandong University School of Control Science and Engineering China Ministry of Education Key Laboratory of Machine Intelligence and System Control China Shandong University School of software Shandong Jinan China Shandong University School of Computer Science and Technology China Shanghai University School of Communication and Information Engineering Shanghai China De Montfort University School of Engineering and Sustainable Development LeicesterLE1 9BH United Kingdom

By converting low-frame-rate, low-resolution videos into high-frame-rate, high-resolution ones, space-time video super-resolution techniques can enhance visual experiences and facilitate more efficient information dissemination. We propose a convolutional neural network (CNN) for space-time video super-resolution, namely GIRNet. Our method combines long-term global information and short-term local information from the video to better extract complete and accurate spatial-temporal information. To generate highly accurate features and thus improve performance, the proposed network integrates a feature-level temporal interpolation module with deformable convolutions and a global spatial-temporal information-based residual convolutional long short-term memory (convLSTM) module. In the feature-level temporal interpolation module, we leverage deformable convolution, which adapts to deformations and scale variations of objects across different scene locations. This provides a more efficient solution than conventional convolution for extracting features from moving objects. Our network effectively uses forward and backward feature information to determine inter-frame offsets, leading to the direct generation of interpolated frame features. In the global spatial-temporal information-based residual convLSTM module, the first convLSTM is used to derive global spatial-temporal information from the input features, and the second convLSTM uses the previously computed global spatial-temporal information feature as its initial cell state. This second convLSTM adopts residual connections to preserve spatial information, thereby enhancing the output features. Experiments on the Vimeo90K dataset show that the proposed method outperforms open source state-of-the-art techniques in peak signal-to-noise-ratio (by 1.45 dB, 1.14 dB, and 0.2 dB over STARnet, TMNet, and 3DAttGAN, respectively), structural similarity index(by 0.027, 0.023, and 0.006 over STARnet, TMNet, and 3DAttGAN, respectiv

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

STMDNet: A Lightweight Directional Framework for Motion Pattern Recognition of Tiny Targets

arXiv

引用

arXiv 2025年

作者： Xu, Mingshuo Luan, Hao Hao, Zhou Daniel Peng, Jigen Yue, Shigang The School of Mathematics and Computing Science University of Leicester LeicesterLE1 7RH United Kingdom The Tianjin Key Laboratory of Information Sensing and Intelligent Control School of Automation and Electrical Engineering Tianjin University of Technology and Education Tuanjin 300222 China The Machine Life and Intelligence Research Center Guangzhou University Guangzhou510006 China

Recognizing motions of tiny targets—only few dozen pixels—in cluttered backgrounds remains a fundamental challenge when standard feature-based or deep learning methods fail under scarce visual cues. We propose STMDNet, a model-based computational framework to Recognize motions of tiny targets at variable velocities under low-sampling frequency scenarios. STMDNet designs a novel dual-dynamics-and-correlation mechanism, harnessing ipsilateral excitation to integrate target cues and leakage-enhancing-type contralateral inhibition to suppress large-object and background motion interference. Moreover, we develop the first collaborative directional encoding-decoding strategy that determines the motion direction from only one correlation per spatial location, cutting computational costs to one-eighth of prior methods. Further, simply substituting the backbone of a strong STMD model with STMDNet raises AUC by 24%, yielding an enhanced STMDNet-F. Evaluations on real-world low-sampling frequency datasets show state-of-the-art results, surpassing the deep learning baseline. Across diverse speeds, STMDNet-F improves mF1 by 19%, 16%, and 8% at 240Hz, 120Hz, and 60Hz, respectively, while STMDNet achieves 87 FPS on a single CPU thread. These advances highlight STMDNet as a next-generation backbone for tiny target motion pattern recognition and underscore its broader potential to revitalize model-based visual approaches in motion detection. Code is available at https://***/MingshuoXu/STMDNet. Copyright © 2025, The Authors. All rights reserved.

关键词： Signal encoding

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：