检索结果-内蒙古大学图书馆

IEEE Conference on Global Communications (GLOBECOM)

作者： Chaoqun Liu Xuanpeng Li Chen Gong Guangyu Li PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security Nanjing University of Science and Technology Southeast University Nanjing China

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

Traffic prediction is an indispensable component of urban planning and traffic management. Achieving accurate traffic prediction hinges on the ability to capture the potential spatio-temporal relationships among road sensors. However, the majority of existing works focus on local short-term spatiotemporal correlations, failing to fully consider the interactions of different sensors in the long-term state. In addition, these works do not analyze the influences of anomalous factors, or have insufficient ability to extract personalized features of anomalous factors, which make them ineffectively capture their spatiotemporal influences on traffic prediction. To address the aforementioned issues, We propose a global spatio-temporal fusionbased traffic prediction algorithm that incorporates anomaly awareness. Initially, based on the designed anomaly detection network, we construct an efficient anomalous factors impacting module (AFIM), to evaluate the spatio-temporal impact of unexpected external events on traffic prediction. Furthermore, we propose a multi-scale spatio-temporal feature fusion module (MTSFFL) based on the transformer architecture, to obtain all possible both long and short term correlations among different sensors in a wide-area traffic environment for accurate prediction of traffic flow. Finally, experiments are implemented based on real-scenario public transportation datasets (PEMS04 and PEMS08) to demonstrate that our approach can achieve stateof-the-art performance.

关键词： Correlation Accuracy Roads Urban planning Sensor fusion Prediction algorithms Feature extraction Transformers Sensors Spatiotemporal phenomena

来源：评论

学校读者我要写书评

暂无评论

Daytime-Mixed Non-Aligned Learning for Real Nighttime Image Enhancement

引用

IEEE TRANSACTIONS ON intelligent TRANSPORTATION SYSTEMS 2025年

作者： Weng, Jiangwei Fan, Junkai Qian, Jianjun Zou, Haiyang Tai, Ying Yang, Jian Li, Jun Nanjing Univ Sci & Technol Sch Comp Sci & Engn PCA Lab Key Lab Intelligent Percept & Syst High Dimens Inf Nanjing 210000 Jiangsu Peoples R China Nanjing Univ Sci & Technol Jiangsu Key Lab Image & Video Understanding Social Sch Comp Sci & Engn Nanjing 210000 Jiangsu Peoples R China China West Normal Univ Sch Comp Sci Nanchong 637009 Peoples R China Nanjing Univ Sch Intelligence Sci & Technol Suzhou 215163 Peoples R China

Enhancing real nighttime images is a significant challenge due to the deterioration of visual quality caused by limited perceptibility under adverse illumination conditions, leading to loss of details and color deviation. In this paper, we propose a novel nighttime image enhancement framework using daytime-mixed non-aligned supervision. It aims to couple the information between non-aligned daytime and nighttime image pairs. Specifically, our framework consists of a simple yet effective daytime-mixed supervised learning phase and a Retinex-based reconstruction phase. In the first phase, we employ a multi-instance with adaptive information fusion (AIF) module integrated within a UNet enhancement network called MIFUNet, which is trained via a daytime-mixed supervised loss. In the second phase, the Retinex-based reconstruction employs both a light-effect estimation network and an illumination adjustment network to restore the nighttime image, guided by physical principles. To evaluate the effectiveness of our approach, we collect a real non-aligned day-night dataset named the NANE dataset, which contains 748 non-aligned image pairs and 100 nighttime images solely for testing. Extensive experiments demonstrate that our method achieves superior performance compared to state-of-the-art image enhancement methods.

关键词： Image enhancement Lighting Image color analysis Training Supervised learning Translation Reflectivity Signal to noise ratio Image restoration Image reconstruction Deep learning daytime-mixed reference nighttime image enhancement non-aligned learning retinex theory

来源：评论

学校读者我要写书评

暂无评论

Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video 39

Depth-Centric Dehazing and Depth-Estimation from Real-World ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Fan, Junkai Wang, Kun Yan, Zhiqiang Chen, Xiang Gao, Shangbing Li, Jun Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China Huaiyin Institute of Technology China

ISBN: (纸本)157735897X

In this paper, we study the challenging problem of simultaneously removing haze and estimating depth from real monocular hazy videos. These tasks are inherently complementary: enhanced depth estimation improves dehazing via the atmospheric scattering model (ASM), while superior dehazing contributes to more accurate depth estimation through the brightness consistency constraint (BCC). To tackle these intertwined tasks, we propose a novel depth-centric learning framework that integrates the ASM model with the BCC constraint. Our key idea is that both ASM and BCC rely on a shared depth estimation network. This network simultaneously exploits adjacent dehazed frames to enhance depth estimation via BCC and uses the refined depth cues to more effectively remove haze through ASM. Additionally, we leverage a non-aligned clear video and its estimated depth to independently regularize the dehazing and depth estimation networks. This is achieved by designing two discriminator networks: DMFIR enhances high-frequency details in dehazed videos, and DMDR reduces the occurrence of black holes in low-texture regions. Extensive experiments demonstrate the proposed method outperforms current state-of-the-art techniques in both video dehazing and depth estimation tasks, especially in real-world hazy scenes. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Discriminators

来源：评论

学校读者我要写书评

暂无评论

LiDAR-SGMOS: Semantics-Guided Moving Object Segmentation with 3D LiDAR

LiDAR-SGMOS: Semantics-Guided Moving Object Segmentation wit...

引用

IEEE/RSJ International Conference on intelligent Robots and Systems (IROS)

作者： Gu, Shuo Yao, Suling Yang, Jian Xu, Chengzhong Kong, Hui Nanjing Univ Sci & Technol Sch Comp Sci & Engn Jiangsu Key Lab Image & Video Understanding Socia PCA LabKey Lab Intelligent Percept & Syst High Nanjing 210094 Peoples R China Univ Macau State Key Lab Internet Things Smart City SKL IOTS Macau 519000 Peoples R China

ISBN: (纸本)9781665491907

Most of the existing moving object segmentation (MOS) methods regard MOS as an independent task, in this paper, we associate the MOS task with semantic segmentation, and propose a semantics-guided network for moving object segmentation (LiDAR-SGMOS). We first transform the range image and semantic features of the past scan into the range view of current scan based on the relative pose between scans. The residual image is obtained by calculating the normalized absolute difference between the current and transformed range images. Then, we apply a Meta-Kernel based cross scan fusion (CSF) module to adaptively fuse the range images and semantic features of current scan, the residual image and transformed features. Finally, the fused features with rich motion and semantic information are processed to obtain reliable MOS results. We also introduce a residual image augmentation method to further improve the MOS performance. Our method outperforms most LiDAR-MOS methods with only two sequential LiDAR scans as inputs on the SemanticKITTI MOS dataset.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

LATEXBLEND: Scaling Multi-concept Customized Generation with Latent Textual Blending

arXiv

引用

arXiv 2025年

作者： Jin, Jian Yu, Zhenbo Shen, Yang Fu, Zhenyong Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Sci. & Tech. China

Customized text-to-image generation renders user-specified concepts into novel contexts based on textual prompts. Scaling the number of concepts in customized generation meets a broader demand for user creation, whereas existing methods face challenges with generation quality and computational efficiency. In this paper, we propose LATEXBLEND, a novel framework for effectively and efficiently scaling multi-concept customized generation. The core idea of LATEXBLEND is to represent single concepts and blend multiple concepts within a Latent Textual space, which is positioned after the text encoder and a linear projection. LATEXBLEND customizes each concept individually, storing them in a concept bank with a compact representation of latent textual features that captures sufficient concept information to ensure high fidelity. At inference, concepts from the bank can be freely and seamlessly combined in the latent textual space, offering two key merits for multi-concept generation: 1) excellent scalability, and 2) significant reduction of denoising deviation, preserving coherent layouts. Extensive experiments demonstrate that LATEXBLEND can flexibly integrate multiple customized concepts with harmonious structures and high subject fidelity, substantially outperforming baselines in both generation quality and computational efficiency. Project Page. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cost-Effective Incremental Deep Model: Matching Model Capacity With the Least Sampling

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2023年第4期35卷 3575-3588页

作者： Yang, Yang Zhou, Da-Wei Zhan, De-Chuan Xiong, Hui Jiang, Yuan Yang, Jian Nanjing Univ Sci & Technol PCA Lab Jiangsu Key Lab Image & Video Understanding Social Key Lab Intelligent Percept & Syst High Dimens Inf Nanjing 210094 Jiangsu Peoples R China Southeast Univ Key Lab Comp Network & Informat Integrat Minist Educ Nanjing 211189 Jiangsu Peoples R China Nanjing Univ State Key Lab Novel Software Technol Nanjing 210094 Jiangsu Peoples R China Nanjing Univ Natl Key Lab Novel Software Technol Nanjing 210023 Jiangsu Peoples R China Rutgers State Univ Rutgers Business Sch Management Sci & Informat Syst Dept Newark NJ 07102 USA

Most existing approaches often utilize the pre-fixed structure and large number of labeled data for training complex deep models, which are difficult to implement on incremental scenarios. As a matter of fact, real-world data is always in stream form. Thereby, there exits two challenges for building incremental deep models: a) Capacity Scalability. The entire training data is not available before learning the task. It is a challenge to make the deep model structure scale with streaming data for flexible model evolution and faster convergence. b) Capacity Sustainability. The distribution streaming data usually changes in nature (concept drift), thus it is necessary to update the model while preserving previous knowledge for overcoming the catastrophic forgetting. To this end, we develop an incremental deep model (IDM), which expands the network structure according to streaming data and slows down forgetting with the adaptive fisher regularization. However, IDM ignores another significant challenge with streaming data: c) Capacity Demand. Training a deep model always needs a large amount of labeled data, whereas it is almost impossible to label all unlabeled instances in real time. The core problem is to select a small number of the most discriminative instances to label while keeping the predictive accuracy of the model. Thereby, we focus on the online semi-supervised learning scenario with abrupt changes in data distribution, and further improve IDM to a cost-effective incremental deep model (CE-IDM), which can adaptively select the most discriminative newly coming instances for query to reduce the manual labeling costs. Specifically, CE-IDM adopts a novel extensible deep network structure by using an extra attention model for hidden layers. Based on the adaptive attention weights, CE-IDM develops a novel instance selection criterion by jointly estimating unlabeled instances' representative and informative degree to satisfy the capacity demand. With the newly labele

关键词： Data models Adaptation models Training Task analysis Sustainable development Scalability labeling Incremental deep learning active sampling capacity scalability capacity sustainability capacity demand

来源：评论

学校读者我要写书评

暂无评论

Video Rescaling With Recurrent Diffusion

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第10期34卷 9386-9399页

作者： Li, Dingyi Liu, Yu Wang, Zengfu Yang, Jian Nanjing Univ Sci & Technol Sch Comp Sci & Engn Key Lab Intelligent Percept & Syst High Dimens Inf PCA LabMinist Educ Nanjing 210094 Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Jiangsu Key Lab Image & Video Understanding Social Nanjing 210094 Peoples R China Hefei Univ Technol Dept Biomed Engn Hefei 230009 Peoples R China Chinese Acad Sci Inst Intelligent Machines Hefei 230031 Peoples R China Univ Sci & Technol China Dept Automat Hefei 230027 Peoples R China

Video rescaling helps to fit different display devices. In video rescaling systems, videos are downsampled for easier storage, transmission and preview. The downsampled videos can be upsampled with a neural network to restore the details when needed. Previous group-based video rescaling algorithms benefit from the joint downsampling and joint upsampling of multiple frames, but are restricted by the fully joint operation. In this paper, we propose a recurrent diffusion-based framework for video rescaling. We employ biased joint operation and recurrent diffusion, to make a better use of the temporal relation within different frames in each image group. We explicitly control the direction of information propagation by arranging the processing order of all frames. In biased joint operation, we concentrate on restoring one frame, i.e., the middle frame. The other frames in the group are coarsely reconstructed. Our recurrent diffusion compensates the coarse frames by gradually propagating information from the middle to borders backwardly and forwardly. The recurrent diffusion module is performed by fusing the information of adjacent frames. Biased joint operation and recurrent diffusion are jointly trained. We design several propagation variants and find that our recurrent diffusion is the best among them. It is also shown that recurrent diffusion is better than non-recurrent diffusion in terms of reconstruction quality and model size. We also adopt a high-resolution fine-tuning strategy to further improve the quality of high-resolution frames. Experimental results demonstrate the effectiveness of the proposed method in terms of visual quality, quantitative evaluations, and computational efficiency. The code will be released at https://***/5ofwind/RDVR.

关键词： Superresolution Image restoration Circuits and systems Image reconstruction Interpolation Recurrent neural networks Computational modeling Video rescaling biased operation information diffusion information fusion recurrent neural networks (RNNs)

来源：评论

学校读者我要写书评

暂无评论

A Gate Recurrent Unit Based Convolutional Neural Network Approach for Pharmacokinetic Parameter Reconstruction 22

A Gate Recurrent Unit Based Convolutional Neural Network App...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Zhang, Lizhi Li, Jintao Tang, Zijian Chu, Mengxiang He, Xiaowei Guo, Hongbo The Xi'an Key Lab of Radiomics and Intelligent Perception Xi'an China School of Information Science and Technology Northwest University Shaanxi Xi'an China

ISBN: (纸本)9798331520526

To address the challenges of selecting regularization parameters and the high computational cost associated with traditional algorithms in reconstructing pharmacokinetic parameters of fluorescent probes, this paper introduces a Gate Recurrent Unit-based Convolutional Neural Network (GRU-CNN). Initially, a simulation program based on the two-compartment model of diffusion equation and pharma-cokinetics is employed to generate time series data of surface measurement signal distributions, which serve as the training set. A convolutional encoder with a dual-pool sampling strategy is utilized to extract crucial features from 2D image sequences. Secondly, a decoder composed of gated recurrent units processes the feature sequences, capturing temporal information and correlating features across frames to produce images that accurately match the input fluorescence probe parameters. Finally, the GRU-CNN is applied to reconstruct metabolic parameter images from the time series data of surface fluorescence distribution in the testing set. Experiment results demonstrate that GRU-CNN reconstructs pharmacokinetic parameters of fluorescent probes in various organs more rapidly and accurately than alternative methods, effectively capturing the pharmacokinetic processes of these probes. © 2025 IEEE.

关键词： Convolutional Neural Network fluorescent probes Gate Recurrent Unit pharmacokinetic parameters

来源：评论

学校读者我要写书评

暂无评论

Geometry-Aware Network for Unsupervised Learning of Monocular Camera's Ego-Motion

引用

IEEE TRANSACTIONS ON intelligent TRANSPORTATION SYSTEMS 2023年第12期24卷 14226-14236页

作者： Zhou, Beibei Xie, Jin Jin, Zhong Kong, Hui Nanjing Univ Sci & Technol Sch Comp Sci & Engn PCA Lab Key Lab Intelligent Percept & Syst High Dimens Inf Nanjing 210094 Jiangsu Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Jiangsu Key Laboratoryof Image & Video Understandi Nanjing 210094 Jiangsu Peoples R China Univ Macau Dept Electromech Engn EME State Key Lab Internet Things Smart City SKL IOTSC Macau Peoples R China

Deep neural networks have been shown to be effective for unsupervised monocular visual odometry that can predict the camera's ego-motion based on an input of monocular video sequence. However, most existing unsupervised monocular methods haven't fully exploited the extracted information from both local geometric structure and visual appearance of the scenes, resulting in degraded performance. In this paper, a novel geometry-aware network is proposed to predict the camera's ego-motion by learning representations in both 2D and 3D space. First, to extract geometry-aware features, we design an RGB-PointCloud feature fusion module to capture information from both geometric structure and the visual appearance of the scenes by fusing local geometric features from depth-map-derived point clouds and visual features from RGB images. Furthermore, the fusion module can adaptively allocate different weights to the two types of features to emphasize important regions. Then, we devise a relevant feature filtering module to build consistency between the two views and preserve informative features with high relevance. It can capture the correlation of frame pairs in the feature-embedding space by attention mechanisms. Finally, the obtained features are fed into the pose estimator to recover the 6-DoF poses of the camera. Extensive experiments show that our method achieves promising results among the unsupervised monocular deep learning methods on the KITTI odometry and TUM-RGBD datasets.

关键词： Index Terms-Monocular visual odometry geometry-aware point clouds visual appearance 6-DoF poses

来源：评论

学校读者我要写书评

暂无评论

Adaptive Pedestrian Trajectory Prediction via Target-Directed Angle Augmentation

Adaptive Pedestrian Trajectory Prediction via Target-Directe...

引用

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

作者： Hao Kong Jie Xu Shenjian Gong Jian Yang Shanshan Zhang PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

Pedestrian trajectory prediction is an important task for many applications such as autonomous driving and surveillance systems. Yet the prediction performance drops dramatically when applying a model trained on the source domain to a new target domain. Therefore, it is of great importance to adapt a predictor to a new domain. Previous works mainly focus on feature-level alignment to solve this problem. In contrast, we solve it from a new perspective of instance-level alignment. Specifically, we first point out one key factor of the domain gaps, i.e., trajectory angles, and then augment the source training data by target-directed orientation augmentation so that its distribution matches with that of the target data. In this way, the trajectory predictor trained on the aligned source data performs better on the target domain. Experiments on standard baselines show that our method improves the state of the art by a large margin. The source code is available at https://***/NeoKH/PTP-DA.

关键词：

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：