检索结果-内蒙古大学图书馆

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Wanru Song Jieying Zheng Yahong Wu Changhong Chen Feng Liu Department of Telecommunication Nanjing Univ. Posts & Telecommun. Nanjing China Jiangsu Key Lab of Image Processing & Image Communications Nanjing Univ. Posts & Telecommun. Nanjing China

Person re-identification has gradually become a hot research topic in many fields, such as security, criminal investigation and video analysis. In this paper, we propose a novel feature extraction framework for video-based person re-identification, namely, the partial attribute-driven network (PADNet). The proposed method is based on the deep-learning architecture and incorporates the attribute and identity learning of the pedestrian. Existing attribute research always focuses on the feature representation at the global-level. Unlike them, first, the pedestrian is automatically partitioned to several body parts in our work. Then the pedestrian and his/her body parts are annotated by the global and partial attributes, respectively. Finally, we employ a four-branch multi-label network to explore the spatial-temporal cues of videos by utilizing these labeled samples. Extensive experiments are conducted on two video-based datasets, including PRID2011 and iLIDS-VID. The experimental results demonstrate the superiority and effectiveness of the proposed PADNet over the state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Constrained Pseudo-labeling for Unsupervised Person Re-identification via GCN Inference 18th

Spatial-Temporal Constrained Pseudo-labeling for Unsupervis...

引用

18th International Forum of Digital Multimedia communication, IFTC 2021

作者： Ling, Sen Yang, Hua Liu, Chuang Chen, Lin Zhao, Hongtian The Institute of Image Communication and Network Engineering Department of Electronic Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Digital Media Processing and Transmission Shanghai Jiao Tong University Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9789811922657

Most existing unsupervised person re-identification (Re-ID) methods primarily depend on the cluster distance, and merely exploit the available source labeled data to assign pseudo labels for the unannotated data. Whereas, the cluster distance usually fails to adapt to different datasets due to the domain gap. Besides, learning exclusively from the source data can not generate accurate pseudo labels for the lack of the target data information. To address this problem, we propose to exploit the spatial-temporal constraints to facilitate the pseudo label generation process. Specifically, graphs for the labeled source data are constructed and the graph convolution network (GCN) is used to learn graph embeddings. Based on these graph embeddings, the likelihood of linkages between graph nodes is estimated and utilized to assign pseudo labels for the unlabeled data. Then, with the pseudo labels, a smoothed spatial-temporal probability distribution model is generated to amend the likelihood of linkages between graph nodes as well as correct the visual similarity scores for person Re-ID. Finally, we optimize the pseudo label assignment, feature extraction networks, and spatial-temporal model alternatively and iteratively to improve the person Re-ID performance. Comprehensive experiments demonstrate that the proposed method outperforms state-of-the-art methods. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Dual-Mode iterative denoiser: Tackling the weak label for anomaly detection

Dual-Mode iterative denoiser: Tackling the weak label for an...

引用

International Conference on Pattern Recognition

作者： Shuheng Lin Hua Yang Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai key lab of digital media processing and transmission Shanghai China

Crowd anomaly detection suffers from limited training data under weak supervision. In this paper, we propose a dual-mode iterative denoiser to tackle the weak label challenge for anomaly detection. First, we use a convolution autoencoder (CAE) in image space to act as a cluster for grouping similar video clips, where the spatial-temporal similarity helps the cluster metric to represent the reconstruction error. Then we use the graph convolution neural network (GCN) to explore the temporal correlation and the feature similarity between video clips within different rough labels, where the classifier can be constantly updated in the label denoising process. Without specific image-level labels, our model can predict the clip-level anomaly probabilities for videos. Extensive experiment results on two public datasets show that our approach performs favorably against the state-of-the-art methods.

关键词： Training Convolution Noise reduction Neural networks Training data Predictive models Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Physics-Environment Interaction Network for Dense Crowd Behavior Recognition

SSRN

引用

SSRN 2024年

作者： Yu, Jiaqi Zhou, Yanshan Pan, Renjie Lai, Pingrui Yang, Hua Institute of Image Communication and Network Engineering Shanghai Key Lab of Digital Media Processing and Transmission Shanghai Jiao Tong University Shanghai200240 China

The analysis of large-scale crowd behavior plays a crucial role in public safety. However, intelligent systems face three major challenges in analyzing dense crowd behavior: the severe occlusion between individuals, the variability in behavior patterns, and the complexity of behavioral evolution. To address these challenges, we propose the Physics-Environment Interaction Network (PEIN), which directly models the motion characteristics of a group with its physics attributes. Specifically, our method consists of two streams. The first stream is the physics-informed crowd property stream, which leverages on the similarity between dense crowd motion and fluid dynamics, using the Navier-Stokes (N-S) equation from fluid mechanics as the modeling framework to describe crowd motion. Considering the inherent relationship between the terms in the N-S equation and various crowd properties (collectiveness, conflict, uniformity and stability), we model these terms with operators and neural networks guided by these crowd properties, enabling the modeling of crowd motion characteristic without relying on the extraction of individual motion information. The second stream is the environment perception stream. Considering that the physics-informed crowd property stream mainly focuses on instantaneous information and that scenes with dense crowd behavior have variability, we introduce a 3D network to enhance the model's robustness. This stream can extract global spatiotemporal information from input video frames, providing a comprehensive perception of the surrounding crowd environment. Since the two streams process different data sources, we design a dual cross-attention mechanism to to enable between features from different modalities, resulting in a joint learnable representation for the final crowd behavior recognition. By incorporating physical laws as constraints, we design a physics-informed loss function combined with a crowd behavior loss function to optimize the model. Consi

关键词： Navier Stokes equations

来源：评论

学校读者我要写书评

暂无评论

引用

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

作者： Jinhai Yang Hua Yang Institution of Image Communication and Network Engineering Shanghai Jiao Tong University China Shanghai Key Lab of Digital Media Processing and Transmission Shanghai China

Few-shot learning aims for rapid adaptation with few samples. Recently, cross-granularity few-shot learning has emerged as a promising research area, where models observe coarse labels but target fine-grained recognition among novel classes. As coarse supervision tends to eliminate feature discrimination among underlying sub-classes, existing methods commonly utilize self-supervision as a complement to explore intra-class variation. However, current methods suffer from an intrinsic conflict between contrastive learning and coarse supervision. In this paper, we locate the root cause of the intrinsic conflict. Then, we resolve it by exploiting the similarity among augmented views while ignoring the unreasonable constraint between negative pairs. Besides, we decouple contrastive learning and coarse supervision into parallel branches to better regularize the latent space. Albeit simple, our approach consistently outperforms state-of-the-art methods across different benchmarks.

关键词： Adaptation models Target recognition Semantics Signal processing Performance gain Benchmark testing Acoustics

来源：评论

学校读者我要写书评

暂无评论

A novel saliency detection model based on curvelet transform

A novel saliency detection model based on curvelet transform

引用

International Conference on Wireless communications and Signal processing (WCSP)

作者： Peiqing Bai Ziguan Cui Zongliang Gan Guijin Tang Feng Liu Image Processing & Image Communication Lab Nanjing University of Posts & Telecommunications Nanjing China Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing University of Posts & Telecommunications Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

ISBN: (纸本)9781509028610

Visually salient object or region detection in images is an active research field in recent years. Inspired by that curvelets can provide multi-scale sparse representation of objects with edges and textures, in this paper, we propose a novel saliency detection model based on fast discrete curvelet transform (SDCT) to detect more compact salient objects in an image. First, fast discrete curvelet transform is used to acquire multi-scale representation of feature maps in CIElab color space. Then the feature maps are transformed to feature salient maps based on dissimilarity measure between patches in a global manner. Finally, the complementary feature salient maps at each scale and each color channel are merged linearly to obtain unitary saliency map. Experimental results on MSRA saliency benchmark database show that the proposed SDCT model outperforms the most state-of-the-art saliency detection models in spatial and frequency domain with higher overall performance, especially acquires more compact salient object and suppresses background saliency effectively, which is desirable for many computer vision applications.

关键词： Transforms Feature extraction image color analysis Frequency-domain analysis Computational modeling Visualization image edge detection

来源：评论

学校读者我要写书评

暂无评论

Adaptive mutation particle filter based on diversity guidance

Adaptive mutation particle filter based on diversity guidanc...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Jin-Xia Yu Yong-Li Tang Wen-Jing Liu College of Computer Science and Technology Henan Polytechnic University Jiaozuo China Jiangsu Provincial Key Laboratory of Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing China Department of Computer Science and Technology Tsinghua University Beijing China

Aimed at the deficiency of the resampling algorithm in PF, diversity measures ESS (effective sample size) and PDF (population diversity factor) are evaluated respectively. Combined with the estimation result, diversity measures PDF is used for adaptively tuning the resampling threshold. By integrating the operation of particle mutation after resampling into PF and using the above mechanism of diversity guidance, the AMPF algorithm (Adaptive Mutation PF) is presented so as to assure the diversity of particle sets. With the simulation program using matlab 7.0 to track a single target motion from a fixed visual observation points, the performance of diversity measures and AMPF are evaluated and the validity of the proposed method is verified.

关键词： Particle measurements Atmospheric measurements Particle filters Algorithm design and analysis Mathematical model Tuning Estimation

来源：评论

学校读者我要写书评

暂无评论

Crowd Counting Via Multi-Level Regression With Latent Gaussian Maps

Crowd Counting Via Multi-Level Regression With Latent Gaussi...

引用

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Yukang Gao Hua Yang Institution of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China Shanghai key lab of digital media processing and transmission Shanghai China

Crowd counting still confronts two primary challenges: limited ability to deal with cross density levels caused by fixed density maps and lack of fine-grained or coarse-grained guidance for density estimation. In this paper, a novel end-to-end crowd counting framework via multi-level regression with latent Gaussian maps is proposed, which is consisted of GaussianNet, EstimateNet and Discriminator. GaussianNet is composed of masked Gaussian convolutional blocks and vanillia convolutional layers, to generate latent Gaussian maps adaptively for various density levels. The latent Gaussian maps are then treated as the ground truth density maps for EstimateNet, which outputs density estimations and follows the principle of adversarial learning with Discriminator. Moreover, multi-level losses are combined for density map regression guidance. Extensive experiments on the major public datasets outperform state-of-the-art ones, illustrating the superior validity of the proposed framework.

关键词： Training Convolution Conferences Estimation Acoustics Bayes methods Task analysis

来源：评论

学校读者我要写书评

暂无评论

Attentive semantic exploring for manipulated face detection

arXiv

引用

arXiv 2020年

作者： Chen, Zehao Yang, Hua Institution of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Lab of Degital Media Processing and Transmission Shanghai China

Face manipulation methods develop rapidly in recent years, whose potential risk to society accounts for the emerging of researches on detection methods. However, due to the diversity of manipulation methods and the high quality of fake images, detection methods suffer from a lack of generalization ability. To solve the problem, we find that segmenting images into semantic fragments could be effective, as discriminative defects and distortions are closely related to such fragments. Besides, to highlight discriminative regions in fragments and to measure contribution to the final prediction of each fragment is efficient for the improvement of generalization ability. Therefore, we propose a novel manipulated face detection method based on Multilevel Facial Semantic Segmentation and Cascade Attention Mechanism. To evaluate our method, we reconstruct two datasets: GGFI and FFMI, and also collect two open-source datasets. Experiments on four datasets verify the advantages of our approach against other state-of-the-arts, especially its generalization ability. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Attentive Semantic Exploring for Manipulated Face Detection

Attentive Semantic Exploring for Manipulated Face Detection

引用

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Zehao Chen Hua Yang Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Lab of Digital Media Processing and Transmission Shanghai China

关键词： image segmentation Semantics Diversity methods Feature extraction Face detection Distortion measurement Speech processing

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：