检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Li, Yu-Lei Lu, Yang Li, Jie Wang, Hanzi Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics China Xidian University Video and Image Processing System Laboratory School of Electronic Engineering China

ISBN: (纸本)9781728163277

Recently, some weakly supervised multi-object tracking (MOT) methods learn identity embedding features with pseudo identity labels rather than the high-cost manual ones. However, these pseudo identity labels may contain many false or missing identities, which adversely affect the optimization of tracking networks, resulting in interrupted trajectories of occluded targets. To effectively reconnect the interrupted trajectories caused by noisy pseudo labels, we propose a novel weakly supervised MOT method based on a Trajectory-Reconnecting Transformer (TRTMOT). TRT-MOT performs feature decoupling to extract discriminative embedding features for reconnecting trajectories of occluded targets. Experimental results show that TRTMOT outperforms previous weakly supervised MOT methods by at least +3.6 and +5.6 on MOTA for the MOT17 and MOT20 datasets, respectively. © 2023 IEEE.

关键词： Feature Decoupling Pseudo Identity Labels Trajectory-Reconnecting Transformer Weakly Supervised Multi-Object Tracking

来源：评论

学校读者我要写书评

暂无评论

A superpixel-based CRF saliency detection approach

引用

Neurocomputing 2017年 244卷 19-32页

作者： Wenliang Qiu Xinbo Gao Bing Han Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xi’an 710071 China

Salient object detection, experienced several decades, has been an active and popular topic in computer vision. Although a large amount of detection algorithms have been proposed, the obtained saliency maps are still not satisfying enough. To this end, we proposed a simple and novel supervised algorithm to detect a pure background saliency map using conditional random fields (CRF) and saliency cues. Most existing CRF approaches set up the probabilistic graphical models with pixel-wise eight neighborhood grid-shaped graph, while our superpixel level graph handling can not only simplify the model but also promote the performance due to the superpixel level two-ring with pseudo-background neighborhood system. It is intuitive and easy to interpret. As a result, the saliency maps generated by the proposed model have relatively pure background regions. Extensive experimental evaluations on six benchmark datasets with pixel-wise ground truths validated the robustness and effectiveness of the proposed saliency model.

关键词： Saliency detection Conditional random fields Superpixel Undirected graphical model Saliency model

来源：评论

学校读者我要写书评

暂无评论

Face Sketch Synthesis using E-HMM and Selective Ensemble

Face Sketch Synthesis using E-HMM and Selective Ensemble

引用

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

作者： Juanjuan Zhong Xinbo Gao Chunna Tian Video & Image Processing System Laboratory (VIPSL) Xidian University Xi'an China

In this manuscript, we propose an automatic sketch synthesis algorithm based on embedded hidden Markov model (E-HMM) and selective ensemble strategy. The E-HMM is used to model the nonlinear relationship between a photo-sketch pair firstly, and then a series of pseudo-sketches, which are generated based on several learned models for a given photo, are integrated together with selective ensemble strategy to synthesize a finer face pseudo-sketch. The experimental results illustrate that the proposed algorithm achieves satisfactory effect of sketch synthesis.

关键词： Face recognition Hidden Markov models Information retrieval image databases image reconstruction Machine learning algorithms image processing Laboratories Face detection Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal Discriminative Binary Embedding for Large-Scale Cross-Modal Retrieval

引用

IEEE Transactions on image processing 2016年第10期25卷 4540-4554页

作者： Wang, Di Gao, Xinbo Wang, Xiumei He, Lihuo Yuan, Bo Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xi'an710071 China

Multimodal hashing, which conducts effective and efficient nearest neighbor search across heterogeneous data on large-scale multimedia databases, has been attracting increasing interest, given the explosive growth of multimedia content on the Internet. Recent multimodal hashing research mainly aims at learning the compact binary codes to preserve semantic information given by labels. The overwhelming majority of these methods are similarity preserving approaches which approximate pairwise similarity matrix with Hamming distances between the to-be-learnt binary hash codes. However, these methods ignore the discriminative property in hash learning process, which results in hash codes from different classes undistinguished, and therefore reduces the accuracy and robustness for the nearest neighbor search. To this end, we present a novel multimodal hashing method, named multimodal discriminative binary embedding (MDBE), which focuses on learning discriminative hash codes. First, the proposed method formulates the hash function learning in terms of classification, where the binary codes generated by the learned hash functions are expected to be discriminative. And then, it exploits the label information to discover the shared structures inside heterogeneous data. Finally, the learned structures are preserved for hash codes to produce similar binary codes in the same class. Hence, the proposed MDBE can preserve both discriminability and similarity for hash codes, and will enhance retrieval accuracy. Thorough experiments on benchmark data sets demonstrate that the proposed method achieves excellent accuracy and competitive computational efficiency compared with the state-of-the-art methods for large-scale cross-modal retrieval task. © 2016 IEEE.

关键词： Discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Graphical Representation for Heterogeneous Face Recognition

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2017年第2期39卷 301-312页

作者： Peng, Chunlei Gao, Xinbo Wang, Nannan Li, Jie Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xi'an Shaanxi710071 China State Key Laboratory of Integrated Services Networks School of Electronic Engineering Xidian University Xi'an Shaanxi710071 China State Key Laboratory of Integrated Services Networks School of Telecommunications Engineering Xidian University Xi'an Shaanxi710071 China

Heterogeneous face recognition (HFR) refers to matching face images acquired from different sources (i.e., different sensors or different wavelengths) for identification. HFR plays an important role in both biometrics research and industry. In spite of promising progresses achieved in recent years, HFR is still a challenging problem due to the difficulty to represent two heterogeneous images in a homogeneous manner. Existing HFR methods either represent an image ignoring the spatial information, or rely on a transformation procedure which complicates the recognition task. Considering these problems, we propose a novel graphical representation based HFR method (G-HFR) in this paper. Markov networks are employed to represent heterogeneous image patches separately, which takes the spatial compatibility between neighboring image patches into consideration. A coupled representation similarity metric (CRSM) is designed to measure the similarity between obtained graphical representations. Extensive experiments conducted on multiple HFR scenarios (viewed sketch, forensic sketch, near infrared image, and thermal infrared image) show that the proposed method outperforms state-of-the-art methods. © 1979-2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Level Set Region Based image Segmentation Using Lattice Boltzmann Method

Level Set Region Based Image Segmentation Using Lattice Bolt...

引用

International Conference on Computational Intelligence and Security

作者： Souleymane Balla-Arabe Bin Wang Xinbo Gao Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xi'an China

Solving Level Set Equation (LSE) by using the classical methods, mostly based on finite differences approximations, costs a lot of computer time particularly when processing high dimensional large-scale data. In recent years, the Lattice Boltzmann Method (LBM) has attracted much attention as a fast alternative approach for solving LSE. The LBM is explicit and highly parallelizable. In this paper, we use the LBM to solve the LSE, we propose an Unsigned Pressure Force (UPF) based on region attribute, which can effectively and efficiently stop the contour at weak blurred edges. The experiments on synthetic and real images illustrate the performance of the proposed method.

关键词： image segmentation Mathematical model Level set Equations image edge detection Lattice Boltzmann methods Active contours

来源：评论

学校读者我要写书评

暂无评论

video post-processing with adaptive 3-D filters for wavelet ringing artifact removal

Video post-processing with adaptive 3-D filters for wavelet ...

引用

作者： Marušič, Boštjan Skočir, Primož Tasič, Jurij Košir, Andrej Faculty of Electrical Engineering University of Ljubljana Triaaka 25 Ljubljana Slovenia Laboratory for Digital Signal Image and Video Processing University of Ljubljana Slovenia University of Ljubljana Slovenia University of Ljubljana Faculty of Electrical Engineering Slovenia System Theory and Computing

This paper reports on the suitability of the SUSAN filter for the removal of artifacts that result from quantization errors in wavelet video coding. In this paper two extensions of the original filter are described. The first uses a combination of 2-D spatial filtering followed by 1-D temporal filtering along motion trajectories, while the second extension is a pure 3-D motion compensated SUSAN filter. The SUSAN approach effectively reduces coding artifacts, while preserving the original signal structure, by relying on a simple pixel-difference-based classification procedure. Results reported in the paper clearly indicate that both extensions efficiently reduce ringing that is the prevalent artifact perceived in wavelet-based coded video. Experimental results indicate an increase in perceptual as well as objective (PSNR) decoded video quality, which is competitive with state-of-the-art post-processing algorithms, especially when low computational demands of the proposed approach are taken into account. Copyright © 2005 The Institute of Electronics, Information and Communication Engineers.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

Temporal Consistency Based Deep Face Forgery Detection Network 1

引用

3rd International Conference on Machine Learning for Cyber Security, ML4CS 2020

作者： Peng, Chunlei Zhang, Wenbo Liu, Decheng Wang, Nannan Gao, Xinbo State Key Laboratory of Integrated Services Networks School of Cyber Engineering Xidian University Xi’an710071 China Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xi’an710071 China State Key Laboratory of Integrated Services Networks School of Telecommunications Engineering Xidian University Xi’an710071 China Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing400065 China

ISBN: (数字)9783030624637

ISBN: (纸本)9783030624620

With the rapid development of deep learning techniques as well as increasingly more visual information being made publicly available on the Internet, image translation methods have achieved great progress and encouraging performance. The manipulation and fabrication of visual information has become accessible and difficult to distinguish by the naked eye, which will have adverse effects on cloud and communication security. Thus, face forgery detection techniques have recently attracted increasing attention. Most recent works regard the face forgery detection problem as the typical image classification task, ignoring the exploration of inherent properties of forgery visual information itself. In this paper, we first explore the inherent limitation of fake videos, and find that the temporal consistency could help distinguish fake faces from real faces. A temporal consistency based deep face forgery detection network is proposed to directly detect fake videos when given multiple consistent video frames. The proposed method effectively considers the frame consistency property and achieves promising detection performance. Experimental results on the face forgery detection dataset demonstrate the superior performance of the proposed method. © 2020, Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An efficient MRF embedded level set method for image segmentation

引用

IEEE Transactions on image processing 2015年第1期24卷 9-21页

作者： Yang, Xi Gao, Xinbo Tao, Dacheng Li, Xuelong Li, Jie State Key Laboratory of Integrated Services Networks School of Electronic Engineering Xidian University Xi'an710071 China Centre for Quantum Computation and Intelligent Systems Faculty of Engineering and Information Technology University of Technology Sydney 235 Jones Street UltimoNSW2007 Australia State Key Laboratory of Transient Optics and Photonics Xi'An Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xi'an710119 China Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xi'an710071 China

This paper presents a fast and robust level set method for image segmentation. To enhance the robustness against noise, we embed a Markov random field (MRF) energy function to the conventional level set energy function. This MRF energy function builds the correlation of a pixel with its neighbors and encourages them to fall into the same region. To obtain a fast implementation of the MRF embedded level set model, we explore algebraic multigrid (AMG) and sparse field method (SFM) to increase the time step and decrease the computation domain, respectively. Both AMG and SFM can be conducted in a parallel fashion, which facilitates the processing of our method for big image databases. By comparing the proposed fast and robust level set method with the standard level set method and its popular variants on noisy synthetic images, synthetic aperture radar (SAR) images, medical images, and natural images, we comprehensively demonstrate the new method is robust against various kinds of noises. In particular, the new level set method can segment an image of size 500 x 500 within 3 s on MATLAB R2010b installed in a computer with 3.30-GHz CPU and 4-GB memory. © 2014 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Learning to Reconnect Interrupted Trajectories for Weakly Supervised Multi-Object Tracking

Learning to Reconnect Interrupted Trajectories for Weakly Su...

引用

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

作者： Yu-Lei Li Yang Lu Jie Li Hanzi Wang Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University China Video and Image Processing System Laboratory School of Electronic Engineering Xidian University China

关键词： Technological innovation Target tracking Manuals Signal processing Feature extraction Transformers Trajectory

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：