检索结果-内蒙古大学图书馆

49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kong, Hao Xu, Jie Gong, Shenjian Yang, Jian Zhang, Shanshan Nanjing Univ Sci & Technol PCA Lab Minist Educ Key Lab Intelligent Percept & Syst HighDimens Inf Nanjing Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Jiangsu Key Lab Image & Video Understanding Socia Nanjing Peoples R China

ISBN: (纸本)9798350344868;9798350344851

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： Trajectory Prediction Domain Adaptation Data Augmentation Feature Extraction

来源：评论

学校读者我要写书评

暂无评论

Pre-Training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation 39

Pre-Training a Density-Aware Pose Transformer for Robust LiD...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： An, Xiaoqi Zhao, Lin Gong, Chen 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

ISBN: (纸本)157735897X

With the rapid development of autonomous driving, LiDAR-based 3D Human Pose Estimation (3D HPE) is becoming a research focus. However, due to the noise and sparsity of LiDAR-captured point clouds, robust human pose estimation remains challenging. Most of the existing methods use temporal information, multi-modal fusion, or SMPL optimization to correct biased results. In this work, we try to obtain sufficient information for 3D HPE only by modeling the intrinsic properties of low-quality point clouds. Hence, a simple yet powerful method is proposed, which provides insights both on modeling and augmentation of point clouds. Specifically, we first propose a concise and effective density-aware pose transformer (DAPT) to get stable keypoint representations. By using a set of joint anchors and a carefully designed exchange module, valid information is extracted from point clouds with different densities. Then 1D heatmaps are utilized to represent the precise locations of the keypoints. Secondly, a comprehensive LiDAR human synthesis and augmentation method is proposed to pre-train the model, enabling it to acquire a better human body prior. We increase the diversity of point clouds by randomly sampling human positions and orientations and by simulating occlusions through the addition of laser-level masks. Extensive experiments have been conducted on multiple datasets, including IMU-annotated LidarHuman26M, SLOPER4D, and manually annotated Waymo Open Dataset v2.0 (Waymo), HumanM3. Our method demonstrates SOTA performance in all scenarios. In particular, compared with LPFormer on Waymo, we reduce the average MPJPE by 10.0mm. Compared with PRN on SLOPER4D, we notably reduce the average MPJPE by 20.7mm. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Human engineering

来源：评论

学校读者我要写书评

暂无评论

DenoDet: Attention as Deformable Multisubspace Feature Denoising for Target Detection in SAR Images

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2025年第2期61卷 4729-4743页

作者： Dai, Yimian Zou, Minrui Li, Yuxuan Li, Xiang Ni, Kang Yang, Jian Nanjing Univ Sci & Technol Sch Comp Sci & Engn Key Lab Intelligent Percept & Syst & High Dimens PCA LabMinist Educ Nanjing 210094 Peoples R China Nanjing Univ Posts & Telecommun Nanjing 210023 Peoples R China Nankai Univ Coll Comp Sci VCIP Tianjin 300350 Peoples R China Nanjing Univ Aeronaut & Astronaut Minist Educ Key Lab Radar Imaging & Microwave Photon Nanjing 211106 Peoples R China

Synthetic aperture radar (SAR) target detection has long been impeded by inherent speckle noise and the prevalence of diminutive ambiguous targets. While deep neural networks have advanced SAR target detection, their intrinsic low-frequency bias and static post-training weights falter with coherent noise and preserving subtle details across heterogeneous terrains. Motivated by traditional SAR image denoising, we propose DenoDet, a network aided by explicit frequency-domain transform to calibrate convolutional biases and pay more attention to high frequencies, forming a natural multiscale subspace representation to detect targets from the perspective of multisubspace denoising. We design TransDeno, a dynamic frequency-domain attention module that performs as a transform-domain soft thresholding operation, dynamically denoising across subspaces by preserving salient target signals and attenuating noise. To adaptively adjust the granularity of subspace processing, we also propose a deformable group fully connected layer that dynamically varies the group conditioned on the input features. Without bells and whistles, our plug-and-play TransDeno sets State-of-the-Art scores on multiple SAR target detection datasets.

关键词： Object detection Frequency-domain analysis Noise Radar polarimetry Feature extraction Noise reduction Synthetic aperture radar Speckle Transforms Accuracy Attention mechanism dynamic thresholding synthetic aperture radar (SAR) target detection transform domain

来源：评论

学校读者我要写书评

暂无评论

Action Candidate Driven Clipped Double Q-Learning for Discrete and Continuous Action Tasks

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第4期35卷 5269-5279页

作者： Jiang, Haobo Li, Guangyu Xie, Jin Yang, Jian Nanjing Univ Sci & Technol PCA Lab Sch Comp Sci & Engn Nanjing 210094 Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Key Lab Intelligent Percept & Syst High Dimens In Minist Educ Nanjing 210094 Peoples R China Nanjing Univ Sci & Technol Jiangsu Key Lab Image & Video Understanding Socia Sch Comp Sci & Engn Nanjing 210094 Peoples R China

Double Q-learning is a popular reinforcement learning algorithm in Markov decision process (MDP) problems. Clipped double Q-learning, as an effective variant of double Q-learning, employs the clipped double estimator to approximate the maximum expected action value. Due to the underestimation bias of the clipped double estimator, the performance of clipped Double Q-learning may be degraded in some stochastic environments. In this article, in order to reduce the underestimation bias, we propose an action candidate-based clipped double estimator (AC-CDE) for Double Q-learning. Specifically, we first select a set of elite action candidates with high action values from one set of estimators. Then, among these candidates, we choose the highest valued action from the other set of estimators. Finally, we use the maximum value in the second set of estimators to clip the action value of the chosen action in the first set of estimators and the clipped value is used for approximating the maximum expected action value. Theoretically, the underestimation bias in our clipped Double Q-learning decays monotonically as the number of action candidates decreases. Moreover, the number of action candidates controls the tradeoff between the overestimation and underestimation biases. In addition, we also extend our clipped Double Q-learning to continuous action tasks via approximating the elite continuous action candidates. We empirically verify that our algorithm can more accurately estimate the maximum expected action value on some toy environments and yield good performance on several benchmark problems. Code is available at https://***/Jiang-HB/ac_CDQ.

关键词： Q-learning Task analysis Benchmark testing Approximation algorithms Toy manufacturing industry Markov processes Learning systems Clipped double Q-learning overestimation bias reinforcement learning underestimation bias

来源：评论

学校读者我要写书评

暂无评论

Dual Manifold Regularization Steered Robust Representation Learning for Point Cloud Analysis 39

Dual Manifold Regularization Steered Robust Representation L...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Bi, Jian Wu, Qianliang Qian, Jianjun Luo, Lei 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

ISBN: (纸本)157735897X

With the rapid advancement of 3D scanning technology, point clouds have become a crucial data type in computer vision and machine learning. However, learning robust representations for point clouds remains a significant challenge due to their irregularity and sparsity. In this paper, we propose a novel Dual Manifold Regularization (DMR) framework that makes full use of the properties of positive and negative curvature in manifolds to improve the representation of point clouds. Specifically, we leverage DMR based on hyperbolic and hyperspherical manifolds to address the limitations of traditional single-manifold regularization techniques, including inadequate generalization ability and adaptability to data diversity, as well as the difficulty of capturing complex relationships between data. To begin, we utilize the tree-like structure of the hyperbolic manifold to model the part-whole hierarchical relationships within point clouds. This allows for a more comprehensive representation of the data, improving the model's capability to understand complex shapes. Additionally, we construct positive samples through topological consistency augmentation and employ contrastive learning techniques in the hyperspherical manifold to capture more discriminative features within the data. Our experimental results show that our method outperforms traditional supervised learning and single-manifold regularization techniques in point cloud analysis. Specifically, for shape classification, DMR achieves a new State-Of-The-Art (SOTA) performance with 94.8% Overall Accuracy (OA) on Model-Net40 and 90.7% OA on ScanObjectNN, surpassing the recent SOTA model without increasing the baseline parameters. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

OKGR: Occluded keypoint Generation and Refinement for 3D Object Detection 6th

OKGR: Occluded Keypoint Generation and Refinement for 3D Obj...

引用

6th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Ji, Mingqian Yang, Jian Zhang, Shanshan Nanjing Univ Sci & Technol PCA Lab Key Lab Intelligent Percept & Syst High Dimens In Minist Educ Nanjing Peoples R China Nanjing Univ Sci & Technol Jiangsu Key Lab Image & Video Understanding Socia Sch Comp Sci & Engn Nanjing Peoples R China

ISBN: (纸本)9789819985548;9789819985555

Lidar-based 3D object detectors utilize point clouds to detect objects in autonomous driving. However, the point clouds are sparse and incomplete, which affects the detectors' learning of shape knowledge and limits the 3D detection performance. Previous works improve performance through completing object shape at the point level or representation level, such as voxel. The former increases computational burden, while the latter has poor generalization ability to point-based detectors. In this paper, we present an approach, namely Occluded keypoint Generation and Refinement (OKGR), which is effective to improve 3D detection performance by completing object features at the keypoint level. Specifically, Occluded keypoint Generation (OKG) generates occluded keypoints to densify raw keypoints and learns the offsets between the generated keypoints and prototypes, while retaining the raw keypoints unchanged. Occluded keypoint Refinement (OKR) assigns weights to the generated keypoints and conducts these weights to features to obtain high-quality complete features for detection. We apply our approach to two representative detectors, PV-RCNN++ and PDV, and evaluate the detectors on KITTI and Waymo Open Dataset. The experiments show significant performance improvement. Particularly, our OKGR applied on PV-RCNN++ achieves improvements ofPedestrian andCyclist of+3.19%,+2.53% APon average difficulty levels on KITTI, and +2.18%, +2.29% mAPH onWaymo Open Dataset. For more information, the supplementary material and code are available at https://***/Mingqj/OKGR.

关键词： 3D Object Detection Point Clouds Object Shape Completion

来源：评论

学校读者我要写书评

暂无评论

Metric Learning-Based Subspace Clustering

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2025年第6期36卷 10491-10503页

作者： Xu, Yesong Chen, Shuo Li, Jun Yang, Jian Anhui Polytech Univ Sch Comp & Informat Wuhu 241000 Peoples R China Nanjing Univ Sch Intelligence Sci & Technol Suzhou Peoples R China Nanjing Univ Sci & Technol PCA Lab Key Lab Intelligent Percept & Syst High Dimens Inf Minist 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

The self-expressive strategy has shown excellent capabilities in realizing low-dimensional representations of high-dimensional data for subspace clustering algorithms. The existing designs, however, are formulated on the linearization assumptions of the data, neglecting the precise characterization of linear relationships within samples. Considering that real-world data adheres to diverse distribution forms, it becomes impractical to first treat the samples as existing in a uniform linear space before finding an appropriate manifold space. To handle this challenge, we propose a novel self-expressive-based learning framework termed metric learning-based subspace clustering (MLSC). Particularly, we smoothly incorporate metric learning into the subspace clustering framework by introducing adaptive neighbors learning and defining a linearity-aware distance to discover the linear manifold space of the original data. We simultaneously utilize the generated representation of the linear structure as input for self-expressiveness to pursue an ideal similarity matrix, which establishes an essential connection with the linearization assumption of the self-expressive strategy. Furthermore, we theoretically demonstrate that our measure can accurately describe the level of linear correlation between instances. Finally, our tests demonstrate that the proposed MLSC attains competitive clustering results compared to state-of-the-art approaches on benchmark datasets.

关键词： Measurement Manifolds Vectors Correlation Optimization Linear regression Image reconstruction High dimensional data Correlation coefficient Clustering methods Linearity-aware low-rank representation metric learning self-expressive subspace clustering

来源：评论

学校读者我要写书评

暂无评论

Class-Wise Contrastive Prototype Learning for Semi-Supervised Classification Under Intersectional Class Mismatch

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2024年 26卷 8145-8156页

作者： Li, Mingyu Zhou, Tao Han, Bo Liu, Tongliang Liang, Xinkai Zhao, Jiajia Gong, Chen Nanjing Univ Sci & Technol Sch Comp Sci & Engn PCA Lab Minist EducKey Lab Intelligent Percept & Syst Hig Nanjing 210094 Peoples R China Hong Kong Baptist Univ Sch Comp Sci Hong Kong Peoples R China Univ Sydney Sch Comp Sci Camperdown NSW 2008 Australia Sci & Technol Complex Syst Control & Intelligent A Beijing 100074 Peoples R China

Traditional Semi-Supervised Learning (SSL) classification methods focus on leveraging unlabeled data to improve the model performance under the setting where labeled set and unlabeled set share the same classes. Nevertheless, the above-mentioned setting is often inconsistent with many real-world circumstances. Practically, both the labeled set and unlabeled set often hold some individual classes, leading to an intersectional class-mismatch setting for SSL. Under this setting, existing SSL methods are often subject to performance degradation attributed to these individual classes. To solve the problem, we propose a Class-wise Contrastive Prototype Learning (CCPL) framework, which can properly utilize the unlabeled data to improve the SSL classification performance. Specifically, we employ a supervised prototype learning strategy and a class-wise contrastive separation strategy to construct a prototype for each known class. To reduce the influence of the individual classes in unlabeled set (i.e., out-of-distribution classes), each unlabeled example can be weighted reasonably based on the prototypes during classifier training, which helps to weaken the negative influence caused by out-of-distribution classes. To reduce the influence of the individual classes in labeled set (i.e., private classes), we present a private assignment suppression strategy to suppress the improper assignments of unlabeled examples to the private classes with the help of the prototypes. Experimental results on four benchmarks and one real-world dataset show that our CCPL has a clear advantage over fourteen representative SSL methods as well as two supervised learning methods under the intersectional class-mismatch setting.

关键词： Prototypes Training Semisupervised learning Perturbation methods Entropy Dogs Computer science Contrastive learning intersectional class mismatch private assignment suppression prototype learning semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Lightweight Efficient Rate-Adaptive Network for Compression-Aware Image Rescaling

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 691-695页

作者： Li, Dingyi Zhang, Yang Liu, Yu Nanjing Univ Sci & Technol Sch Comp Sci & Engn Key Lab Intelligent Percept & Syst High Dimens Inf Minist EducPCA Lab 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

Compression-aware image rescaling approaches convert high-resolution images to compressed low-resolution ones to fit various display devices or save bandwidth/storage. Inverse upscaling is successively performed to enlarge the low-resolution images to the original sizes with rich details. However, previous compression-aware image rescaling methods lack adaptivity to diverse compression rates, or require multiple large models with huge computational cost for adjusting. To overcome these challenges, we propose a lightweight efficient rate-adaptive network (LERAN) for compression-aware image rescaling. We design a non-invertible framework based on quality factor-driven feature modulation modules and an expandable training strategy, to achieve the adaptivity to various compression rates with only one light and efficient model. Moreover, alternative recursive blocks are presented for lighter weights with very small performance drop. During training, we also introduce a sparse low-resolution residual feature loss which promotes easier convergence of the model without adding further computational burden. Extensive experimental results demonstrate that our method significantly outperforms state-of-the-art compression-aware image rescaling approaches for different compression rates on popular benchmarks, with an all-in-one lightweight model and much faster speed.

关键词： Image coding Transform coding Training Modulation Testing Q-factor Adaptation models Convolution Computational modeling Transforms Adaptive efficient image rescaling image compression light-weight

来源：评论

学校读者我要写书评

暂无评论

Inscription-Image Inpainting with Edge Structure Reconstruction 12th

Inscription-Image Inpainting with Edge Structure Reconstruc...

引用

12th International Conference on Image and Graphics, ICIG 2023

作者： Liu, Haonan He, Xuelei Zhu, Jiaxin He, Xiaowei Xi’an Key Lab of Radiomics and Intelligent Perception School of Information Sciences and Technology Northwest University Shaanxi Xi’an China

ISBN: (纸本)9783031463105

Textual relics are particularly crucial for understanding history because they provide written records of past societies and their development. However, inscriptions and calligraphy works are susceptible to varying degrees of pollution or damage, which can cause the characters to be blurry, unclear, or even partially missing, thereby affects the recorded information. Compared with natural images, handwritten ancient inscription images have higher similarity, obvious structural features, clear edges, and explicit semantics. Image restoration techniques have made significant progress, but in textual images areas, they often lack an understanding of the overall structure of the characters and the standardization of stroke details, which can result in unsatisfactory restoration results. An inscription-image inpainting method has been proposed for the automated restoration of damaged inscriptions based on edge detection module and generative adversarial networks, taking into account the characteristics of ancient Chinese inscriptions. The edge detection module used to collect the edge information of the characters’ strokes and lead the network to learn the structure and semantics of the characters. Moreover, a perceptual loss is adopted to enhance the detailed information of features which help to restore characters’ details. A dataset of ancient inscriptions was created from publication, and experiments on this dataset showed that our method has better restoration quality than common natural image restoration methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Edge detection

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：