检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Haoliang Zhao Huizhou Zhou Yongjun Zhang Jie Chen Yitong Yang Yong Zhao Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry State Key Laboratory of Public Big Data College of Computer Science and Technology Institute of Artificial Intelligence Guizhou University Guiyang Guizhou China Ghost-Valley AI Technology Shenzhen Guangdong China School of Physics and Optoelectronic Engineering Guangdong University of Technology Guangzhou China The Key Laboratory of Integrated Microsystems Shenzhen Graduate School Peking University China

In the field of binocular stereo matching, remarkable progress has been made by iterative methods like RAFT-Stereo and CREStereo. However, most of these methods lose information during the iterative process, making it difficult to generate more detailed difference maps that take full advantage of high-frequency information. We propose the Decouple module to alleviate the problem of data coupling and allow features containing subtle details to transfer across the iterations which proves to alleviate the problem significantly in the ablations. To further capture high-frequency details, we propose a Normalization Refinement module that unifies the disparities as a proportion of the disparities over the width of the image, which address the problem of module failure in cross-domain scenarios. Further, with the above improvements, the ResNet-like feature extractor that has not been changed for years becomes a bottleneck. Towards this end, we proposed a multi-scale and multi-stage feature extractor that introduces the channel-wise self-attention mechanism which greatly addresses this bottleneck. Our method (DLNR) ranks 1st on the Middlebury leaderboard, significantly outperforming the next best method by 13.04%. Our method also achieves SOTA performance on the KITTI-2015 benchmark for D1-fg. Code and demos are available at: https://***/David-Zhao-1997/High-frequency-Stereo-Matching-Network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anchor-Based Discriminative Dual Distribution Calibration for Transductive Zero-Shot Learning

SSRN

引用

SSRN 2023年

作者： Zhang, Yi Huang, Sheng Yang, Wanli Tang, Wenhao Zhang, Xiaohong Yang, Dan School of Big Data and Software Engineering Chongqing University No.55 Daxuecheng South Rd. Chongqing Shapingba401331 China Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University No.174 Shazhengjie Chongqing Shapingba400044 China

Zero-shot learning (ZSL) is machine learning task to recognize samples from classes that are not observed during training. Transductive ZSL (TZSL) is a more realistic and effective paradigm that leverages unlabeled unseen data during training to reduce the bias towards seen classes. However, most existing TZSL methods neglect the information gap between visual and semantic spaces, and thus fail to generate distribution-consistent unseen features. To address this issue, we propose a novel TZSL approach named Anchorbased Discriminative Dual Distribution Calibrated Feature Generative Network (AD3C-FGN), which performs anchor-based distribution calibration in both visual and semantic spaces for improving generalization ability of the model. In AD3C-FGN, we adopt conditional generative adversarial network with an unseen discriminator to construct a Y-shape generation model that mitigates the domain shift problem. Moreover, an AD3C module is elaborated for calibrating the distribution of generated and real samples in both visual and semantic spaces with real sample anchors, and also enhance the discriminability of the generated samples. AD3C enforces the generated sample to be closer to its homogenous anchor but farther away from inhomogeneous anchors in both spaces. Extensive experimental results on six popular ZSL benchmarks demonstrate that our method achieves promising performances in different settings. © 2023, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

On the Fine-Grained Crowd Analysis via Passive WiFi Sensing

TechRxiv

引用

TechRxiv 2023年

作者： Hao, Lifei Huang, Baoqi Jia, Bing Mao, Guoqiang The Engineering Research Center of Ecological Big Data Ministry of Education The Inner Mongolia A.R. Key Laboratory of Wireless Networking and Mobile Computing The College of Computer Science Inner Mongolia University Hohhot010021 China The Research Institute of Smart Transportation Xidian University Xi’an710071 China

Regarding the passive WiFi sensing based crowd analysis, this paper first theoretically investigates its limitations, and then proposes a deep learning based scheme targeted for returning fine-grained crowd states in large surveillance areas. To this end, three key challenges are coped with: to relieve the influences of the randomness and sparsity induced by passive WiFi sensing, an attention-based deep convolutional autoencoder model is designed to recover accurate crowd density maps in a way similar to image reconstruction;to combat the anonymity caused by MAC randomization, following the identification of local high-density crowds (LHDCs) with the density clustering algorithm, i.e. DM-DBSCAN, a bidirectional convolutional LSTM based model is employed to infer LHDC speeds;to overcome the absence of passive WiFi sensing datasets for model training, three semi-synthetic datasets are produced by emulating passive WiFi sensing with practical pedestrian tracking datasets. Extensive experiments confirm that, the proposed scheme significantly outperforms existing WiFi-based methods in terms of crowd density estimation and provides superior crowd speed estimation. More importantly, the scheme can also produce consistent crowd states on a real-world dataset, revealing that it has the ability to support accurate, visualized and real-time crowd monitoring in large surveillance areas. © 2023, CC BY-NC-SA.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Pre-ictal causal connectivity reveals the epileptic network characteristics for deep brain stimulation

引用

Neuroscience 2025年 579卷 329-343页

作者： Yifan Wang Tao Yu Yulan Ma Weigang Cui Xueyuan Wang Liankun Ren Yang Li Department of Automation Science and Electrical Engineering Beihang University Beijing 100191 China Beijing Institute of Functional Neurosurgery Department of Functional Neurosurgery Xuanwu Hospital Capital Medical University Beijing 100053 China School of Engineering Medicine Beihang University Beijing 100191 China Department of Neurology Xuanwu Hospital Capital Medical University Beijing 100053 China Beijing Advanced Innovation Center for Big Data and Brain Computing State Key Laboratory of Virtual Reality Technology and Systems Department of Automation Science and Electrical Engineering Beihang University Beijing 100191 China

Deep brain stimulation of anterior nucleus of the thalamus (ANT-DBS) is an effective clinical treatment for drug-resistant focal epilepsy. However, the complex epileptic network characteristics underlying ANT-stimulation effectiveness remain unknown, owing to currently unclear connectivity between ANT and seizure-related cortex in pre-ictal periods. Here, we developed a novel individualized pre-ictal ANT-cortical tripartite connectivity network (PANT-CTCNet), aiming to reveal epileptic network characteristics using intracranial stereo-electroencephalography (sEEG) recordings in five patients with focal epilepsy for 90 trials. Each trial represented a pre-ictal or post-stimulus sEEG duration, which was used to construct the epileptic network. By employing conditional Granger causality, we constructed individualized ANT-cortical connectivity networks and found a common epileptic network centred on ANT closely connected with seizure-related cortex in pre-ictal periods. After ANT stimulation for clinical validation, strengthened pre-ictal connectivity between ANT and epileptogenic zones led to significant decline in the causal intensity of epileptic networks. The PANT-CTCNet can give a quantitative reference for clinical preoperative evaluation of patient suitability for ANT-DBS treatment. These findings regarding epileptic network characteristics provide theoretical basis in the selection of optimal surgical candidates for personalized ANT-DBS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Air Pollution Monitoring By Integrating Local and Global Information in Self-Adaptive Multiscale Transform Domain

引用

IEEE Transactions on Multimedia 2025年 27卷 3716-3728页

作者： Gu, Ke Liu, Yuchen Liu, Hongyan Liu, Bo Qiao, Junfei Lin, Weisi Zhang, Wenjun Beijing University of Technology School of Information Science and Technology Engineering Research Center of Intelligent Perception and Autonomous Control of Ministry of Education Beijing Laboratory of Smart Environmental Protection Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Artificial Intelligence Institute Beijing100124 China Massey University School of Mathematical and Computational Sciences New Zealand Nanyang Technological University College of Computing and Data Science Singapore Shanghai Jiao Tong University Institute of Image Communication and Information Processing Shanghai China

As the deadliest form of pollution, air pollution had a prolonged severe damage to the human health and life safety of nearly 99% of the world's population. Facing to the problem that billions of tons of pollutants discharged into the air per year by industrial activities, this paper proposed a novel image-based air pollution monitor (IAPM) by incorporating local and global information in the self-adaptive multiscale transform domain, so as to achieve the timely and effective leakage detection of typical air pollutants from a single image. To be specific, this paper first developed a screen-shaped module according to two significant findings in visual neuroscience, which include the high sensitivity of human eyes to horizontal and vertical stimuli and the center-surround inhibition, by designing and fusing the square module, horizontal strip module and vertical strip module parallelly for simulating the behaviour of human eyes to extract local features. Second, the learnable weights and proportional mapping were applied to incorporate the screen-shaped module and lightweight vision transformer as backbone, towards more richly exploiting and fusing local and global information just as the way a brain perceives external stimuli. Third, a new self-adaptive multiscale transform domain method was devised based on two motivations from the visual characteristics of multiscale perception and the brain characteristics of self-adaptive domain transform to modify the backbone by using the operations of pooling and pointwise convolution. Extensive experiments implemented on the datasets of carbon particulate matters and ethylene leakage confirmed the superior monitoring performance of the proposed IAPM model beyond the state-of-the-art (SOTA) peers by an accuracy gain of about 4%. Furthermore, the proposed IAPM model only required 0.089 GFLOPs and 0.15 million model parameters, remarkably outperforming SOTA competitors in computational efficiency and storage resources. © 1999-2

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Violence Detection In Videos via Motion-Guided Global and Local Views

Violence Detection In Videos via Motion-Guided Global and Lo...

引用

IEEE International Conference on data Science in Cyberspace (DSC)

作者： Ning Su Lijuan Sun Yutong Gao Jingchen Wu Xu Wu Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Cyberspace Security BUPT School of Economics and Management Beijing University of Posts and Telecommunications Beijing China Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China School of Computer Science (National Pilot Software Engineering School) BUPT

Video violence detection aims to locate the time window in which violent behavior occurs. Most methods focus on utilizing RGB features directly or only fusing RGB and audio features, ignoring the effective exploitation of motion information carried in optical flow. This lack of emphasis on motion information may impact the overall accuracy of violence detection. Moreover, we observe that videos contain strong local correlations, so it is insufficient to analyze only from a holistic perspective without capturing finer details. Therefore, in this paper, we design a novel Global-and-Local Cross-Modal Network (GL-CMN) for violence detection, which effectively integrates motion information and multi-granularity features from target videos. Specifically, we first propose a Motion-Guided Attention Module (MGAM) to obtain enhanced visual features by calibrating RGB features through optical flow features. Secondly, The enhanced features are simultaneously fed into two parallel branches of the network. The global branch fuses the visual and audio features into holistic representations. The local branch extracts multi-scale temporal dependencies through dilated convolutions. Experiments demonstrate that our method exhibits significant improvement compared to previous state-of-the-art methods on the XD-Violence dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentification

arXiv

引用

arXiv 2022年

作者： Wu, Chao Ge, Wenhang Wu, Ancong Chang, Xiaobin School of Artificial Intelligence Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China School of Computer Science and Engineering Sun Yat-sen University China

To learn camera-view invariant features for person Re-IDentification (Re-ID), the cross-camera image pairs of each person play an important role. However, such cross-view training samples could be unavailable under the ISolated Camera Supervised (ISCS) setting, e.g., a surveillance system deployed across distant scenes. To handle this challenging problem, a new pipeline is introduced by synthesizing the cross-camera samples in the feature space for model training. Specifically, the feature encoder and generator are end-to-end optimized under a novel method, Camera-Conditioned Stable Feature Generation (CCSFG). Its joint learning procedure raises concern on the stability of generative model training. Therefore, a new feature generator, σ-Regularized Conditional Variational Autoencoder (σReg. CVAE), is proposed with theoretical and experimental analysis on its robustness. Extensive experiments on two ISCS person Re-ID datasets demonstrate the superiority of our CCSFG to the competitors. 1 © 2022, CC BY.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Optimizing AoI in RIS-aided Wireless Powered Backscatter-Active Communication Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Hu, Huimin Zhang, Ruichen Ding, Zhiguo Jiang, Fan Jiang, Ruihong Niyato, Dusit Xi'an University of Posts and Telecommunications School of Communications and Information Engineering Xi'an710121 China Nanyang Technological University College of Computing and Data Science Singapore Singapore Khalifa University Department of Computer and Information Engineering Abu Dhabi United Arab Emirates Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China

In this paper, we investigate the average age of information (AoI) in wireless powered backscatter-active communication networks (WPBACN) assisted by a reconfigurable intelligent surface (RIS). To minimize the average AoI, we jointly optimize the phase shift of the RIS, the backscatter-active communication time allocation factor, and the transmitted power of IoT devices. Since the optimization problem is composed of coupled variables, the optimization variables are implicit in the objective function and the problem is non-convex, which makes it challenging to solve. To address this challenge, we decompose the problem into an RIS phase shift optimization subproblem and a joint power and time allocation subproblem. Simulation results indicate that the proposed scheme has a significant performance advantage in reducing the average AoI compared to the scheme using random RIS phase shifts and the scheme without RIS and supports the challenging quality of service required by real-time information update applications. © 1967-2012 IEEE.

关键词： age of information Reconfigurable intelligent surface WPBACN

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Relation Matrix Bidirectional Approach for Relational Triple Extraction

Hybrid Deep Relation Matrix Bidirectional Approach for Relat...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Yushuai Hu Jing Zhao Ming Li Lin Yuan Qingzhi Zou Ronghuan Zhang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of Intelligence and Information Engineering Shandong University of Traditional Chinese Medicine Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Relation extraction is a crucial task within information extraction, and numerous models have demonstrated impressive results. However, most of the tagging-based relation triple extraction methods employ unidirectional approaches to extract subjects, objects, and relations, which may overlook crucial information. In this paper, we introduce a novel deep matrix-based bidirectional relation extraction model. Firstly, we extract forward and backward entity pairs. During the bidirectional extraction process,there may be some redundant relationships,so we use a shared encoder to connect and enhance the extraction process. Secondly, we design a low-complexity relation extraction matrix to allocate all possible relations. We assess our model using diverse benchmark datasets, and comprehensive experiments show that our approach effectively addresses subsequent triple extraction issues stemming from entity extraction failures.

关键词： Learning systems Federated learning Computational modeling Benchmark testing Information retrieval data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Real-World Active Speaker Detection with Multi-Modal Extraction Pre-Training

arXiv

引用

arXiv 2024年

作者： Tao, Ruijie Qian, Xinyuan Das, Rohan Kumar Gao, Xiaoxue Wang, Jiadong Li, Haizhou The Department of Electrical and Computer Engineering National University of Singapore Singapore The Department of Computer Science and Technology University of Science and Technology Beijing Beijing100083 China Fortemedia Singapore138637 Singapore Institute for Infocomm Research A*STAR Singapore The Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen518172 China Shenzhen Research Institute of Big data Shenzhen518172 China The Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore The University of Bremen 28359 Germany

Audio-visual active speaker detection (AV-ASD) aims to identify which visible face is speaking in a scene with one or more persons. Most existing AV-ASD methods prioritize capturing speech-lip correspondence. However, there is a noticeable gap in addressing the challenges from real-world AV-ASD scenarios. Due to the presence of low-quality noisy videos in such cases, AV-ASD systems without a selective listening ability are short of effectively filtering out disruptive voice components from mixed audio inputs. In this paper, we propose a Multi-modal Speaker Extraction-to-Detection framework named ‘MuSED’, which is pre-trained with audio-visual target speaker extraction to learn the denoising ability, then it is fine-tuned with the AV-ASD task. Meanwhile, to better capture the multi-modal information and deal with real-world problems such as missing modality, MuSED is modelled on the time domain directly and integrates the multi-modal plus-and-minus augmentation strategy. Our experiments demonstrate that MuSED substantially outperforms the state-of-the-art AV-ASD methods and achieves 95.6% mAP on the AVA-ActiveSpeaker dataset, 98.3% AP on the ASW dataset, and 97.9% F1 on the Columbia AV-ASD dataset, respectively. We will publicly release the code in due course. © 2024, CC BY.

关键词： Extraction

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：