检索结果-内蒙古大学图书馆

30th IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Li, Dangwei Chen, Xiaotang Zhang, Zhang Huang, Kaiqi CASIA CRIPAC Beijing Peoples R China CASIA NLPR Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China CAS Ctr Excellence Brain Sci & Intelligence Techn Beijing Peoples R China

ISBN: (纸本)9781538604571

Person Re-identification (ReID) is to identify the same person across different cameras. It is a challenging task due to the large variations in person pose, occlusion, background clutter, etc. How to extract powerful features is a fundamental problem in ReID and is still an open problem today. In this paper, we design a Multi-Scale Context-Aware Network (MSCAN) to learn powerful features over full body and body parts, which can well capture the local context knowledge by stacking multi-scale convolutions in each layer. Moreover, instead of using predefined rigid parts, we propose to learn and localize deformable pedestrian parts using Spatial Transformer Networks (STN) with novel spatial constraints. the learned body parts can release some difficulties, e.g. pose variations and background clutters, in part-based representation. Finally, we integrate the representation learning processes of full body and body parts into a unified framework for person ReID through multi-class person identification tasks. Extensive evaluations on current challenging large-scale person ReID datasets, including the image-based Market1501, CUHK03 and sequence-based MARS datasets, show that the proposed method achieves the state-of-the-art results.

关键词： Kernel Visualization Machine learning Clutter Feature extraction Image color analysis

来源：评论

学校读者我要写书评

暂无评论

Learning Multifunctional Binary Codes for Both Category and Attribute Oriented Retrieval Tasks 30

Learning Multifunctional Binary Codes for Both Category and ...

引用

30th IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Liu, Haomiao Wang, Ruiping Shan, Shiguang Chen, Xilin Chinese Acad Sci Key Lab Intelligent Informat Proc Inst Comp Technol Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Cooperat Medianet Innovat Ctr Beijing Peoples R China

ISBN: (纸本)9781538604571

In this paper we propose a unified framework to address multiple realistic image retrieval tasks concerning both category and attributes. Considering the scale of modern datasets, hashing is favorable for its low complexity. However, most existing hashing methods are designed to preserve one single kind of similarity, thus incapable of dealing with the different tasks simultaneously. To overcome this limitation, we propose a new hashing method, named Dual Purpose Hashing (DPH), which jointly preserves the category and attribute similarities by exploiting the convolutional networks (CNN) to hierarchically capture the correlations between category and attributes. Since images with both category and attribute labels are scarce, our method is designed to take the abundant partially labelled images on the Internet as training inputs. With such a framework, the binary codes of new-coming images can be readily obtained by quantizing the network outputs of a binary-like layer, and the attributes can be recovered from the codes easily. Experiments on two large-scale datasets show that our dual purpose hash codes can achieve comparable or even better performance than those state-of-the-art methods specifically designed for each individual retrieval task, while being more compact than the compared methods.

关键词： Learning Multifunctional Binary Codes Both Category Attribute Oriented Retrieval Tasks Category binary code hashing method hashing Religious Missions retrieval

来源：评论

学校读者我要写书评

暂无评论

A Global Hypothesis Verification Framework for 3D Object recognition in Clutter

引用

IEEE TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 2016年第7期38卷 1383-1396页

作者： Aldoma, Aitor Tombari, Federico Di Stefano, Luigi Vincze, Markus Vienna Univ Technol Grp ACIN Vision4Robot A-1060 Vienna Austria Univ Bologna CVLAB Grp DISI Bologna Italy

Pipelines to recognize 3D objects despite clutter and occlusions usually end up with a final verification stage whereby recognition hypotheses are validated or dismissed based on how well they explain sensor measurements. Unlike previous work, we propose a Global Hypothesis Verification (GHV) approach which regards all hypotheses jointly so as to account for mutual interactions. GHV provides a principled framework to tackle the complexity of our visual world by leveraging on a plurality of recognition paradigms and cues. Accordingly, we present a 3D object recognition pipeline deploying both global and local 3D features as well as shape and color. thereby, and facilitated by the robustness of the verification process, diverse object hypotheses can be gathered and weak hypotheses need not be suppressed too early to trade sensitivity for specificity. Experiments demonstrate the effectiveness of our proposal, which significantly improves over the state-of-art and attains ideal performance (no false negatives, no false positives) on three out of the six most relevant and challenging benchmark datasets.

关键词： 3D object recognition hypothesis verification correspondence grouping scene understanding

来源：评论

学校读者我要写书评

暂无评论

Oriented Response Networks 30

Oriented Response Networks

引用

30th IEEE/CVF conference on computer vision and pattern recognition (CVPR)

作者： Zhou, Yanzhao Ye, Qixiang Qiu, Qiang Jiao, Jianbin Univ Chinese Acad Sci Beijing Peoples R China Duke Univ Durham NC 27706 USA

ISBN: (纸本)9781538604571

Deep Convolution Neural Networks (DCNNs) are capable of learning unprecedentedly effective image representations. However, their ability in handling significant local and global image rotations remains limited. In this paper, we propose Active Rotating Filters (ARFs) that actively rotate during convolution and produce feature maps with location and orientation explicitly encoded. An ARF acts as a virtual filter bank containing the filter itself and its multiple unmaterialised rotated versions. During back-propagation, an ARF is collectively updated using errors from all its rotated versions. DCNNs using ARFs, referred to as Oriented Response Networks (ORNs), can produce within-class rotation-invariant deep features while maintaining inter-class discrimination for classification tasks. the oriented response produced by ORNs can also be used for image and object orientation estimation tasks. Over multiple state-of-the-art DCNN architectures, such as VGG, ResNet, and STN, we consistently observe that replacing regular filters with the proposed ARFs leads to significant reduction in the number of network parameters and improvement in classification performance. We report the best results on several commonly used benchmarks(1).

关键词： feature map image representation Convolution Filters Oriented network parameters super twisted nematic images Imagery (Psychotherapy) reduction index object orientation

来源：评论

学校读者我要写书评

暂无评论

Scale and Rotation Invariant Approach to Tracking Human Body Part Regions in Videos

Scale and Rotation Invariant Approach to Tracking Human Body...

引用

26th IEEE conference on computer vision and pattern recognition (CVPR)

作者： Bo, Yihang Jiang, Hao Chinese Acad Sci Inst Automat Beijing Peoples R China Boston Coll Dept Comp Sci Chestnut Hill MA 02167 USA

ISBN: (纸本)9780769549903

We propose a novel scale and rotation invariant method to track a human subject's body part regions in cluttered videos. the proposed method optimizes the assembly of body part region proposals with the spatial and temporal constraints of a human body plan. this approach is invariant to the object scale and rotation changes. To enable scale and rotation invariance, the human body part graph of the proposed method has to be loopy;efficiently optimizing the body part region assembly is a great challenge. We propose a dynamic programming method to solve the problem. We devise a method that finds N-best whole body configurations from loopy structures in each video frame using dynamic programming. the N-best configurations are then used to construct trellises with which we track human body part regions by finding shortest paths on the trellises. Our experiments on a variety of videos show that the proposed method is efficient, accurate and robust against object appearance variations, scale and rotation changes and background clutter.

关键词： dynamic programming graph theory object tracking video signal processing

来源：评论

学校读者我要写书评

暂无评论

Human Action recognition Based on Context-Dependent Graph Kernels 27

Human Action Recognition Based on Context-Dependent Graph Ke...

引用

27th IEEE conference on computer vision and pattern recognition (CVPR)

作者： Wu, Baoxin Yuan, Chunfeng Hu, Weiming Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing Peoples R China

ISBN: (纸本)9781479951178

Graphs are a powerful tool to model structured objects, but it is nontrivial to measure the similarity between two graphs. In this paper, we construct a two-graph model to represent human actions by recording the spatial and temporal relationships among local features. We also propose a novel family of context-dependent graph kernels (CGKs) to measure similarity between graphs. First, local features are used as the vertices of the two-graph model and the relationships among local features in the intra-frames and inter-frames are characterized by the edges. then, the proposed CGKs are applied to measure the similarity between actions represented by the two-graph model. Graphs can be decomposed into numbers of primary walk groups with different walk lengths and our CGKs are based on the context-dependent primary walk group matching. Taking advantage of the context information makes the correctly matched primary walk groups dominate in the CGKs and improves the performance of similarity measurement between graphs. Finally, a generalized multiple kernel learning algorithm with a proposed l12-norm regularization is applied to combine these CGKs optimally together and simultaneously train a set of action classifiers. We conduct a series of experiments on several public action datasets. Our approach achieves a comparable performance to the state-of-the-art approaches, which demonstrates the effectiveness of the two-graph model and the CGKs in recognizing human actions.

关键词： Human action recognition context-dependent graph kernels generalized multiple kernel learning two-graph model

来源：评论

学校读者我要写书评

暂无评论

A Probabilistic Framework for Multitarget Tracking with Mutual Occlusions 27

A Probabilistic Framework for Multitarget Tracking with Mutu...

引用

27th IEEE conference on computer vision and pattern recognition (CVPR)

作者： Yang, Menglong Liu, Yiguang Wen, Longyin You, Zhisheng Li, Stan Z. Sichuan Univ Key Lab Fundamental Synthet Vis Graph & Image Nat Sch Aeronaut & Astronaut & Comp Sci Chengdu Peoples R China Chinese Acad Sci Ctr Biometr & Secur Res Beijing 100864 Peoples R China Chinese Acad Sci Natl Lab Pattern Recognit Inst Automat Beijing 100864 Peoples R China

ISBN: (纸本)9781479951178

Mutual occlusions among targets can cause track loss or target position deviation, because the observation likelihood of an occluded target may vanish even when we have the estimated location of the target. this paper presents a novel probability framework for multitarget tracking with mutual occlusions. the primary contribution of this work is the introduction of a vectorial occlusion variable as part of the solution. the occlusion variable describes occlusion states of the targets. this forms the basis of the proposed probability framework, with the following further contributions: 1) Likelihood: A new observation likelihood model is presented, in which the likelihood of an occluded target is computed by referring to both of the occluded and occluding targets. 2) Priori: Markov random field (MRF) is used to model the occlusion priori such that less likely "circular" or "cascading" types of occlusions have lower priori probabilities. Both the occlusion priori and the motion priori take into consideration the state of occlusion. 3) Optimization: A realtime RJMCMC-based algorithm with a new move type called "occlusion state update" is presented. Experimental results show that the proposed framework can handle occlusions well, even including long-duration full occlusions, which may cause tracking failures in the traditional methods.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Fusion of static and dynamic body biometrics for gait recognition

Fusion of static and dynamic body biometrics for gait recogn...

引用

9th IEEE International conference on computer vision

作者： Wang, L Ning, HZ Tan, TN Hu, WM Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit NLPR Beijing 100080 Peoples R China

ISBN: (纸本)0769519504

Human identification at a distance has recently gained growing interest from computer vision researchers. this paper aims to propose a visual recognition algorithm based upon fusion of static and dynamic body biometrics. For each sequence involving a walking figure, pose changes of the segmented moving silhouettes are represented as an associated sequence of complex vector configurations, and are then analyzed using the Procrustes shape analysis method to obtain a compact appearance representation, called static information of body. Also, a model-based approach is presented under,a Condensation framework to track the walker and to recover joint-angle trajectories of lower limbs, called dynamic information of gait. Both static and dynamic cues are respectively used for recognition using the nearest exemplar classifier they are also effectively fused on decision level using different combination rules to improve the performance of both identification and verification. Experimental results on a dataset including 20 subjects demonstrate the validity of the proposed algorithm.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Dual Clustering for Image Semantic Segmentation

Weakly-Supervised Dual Clustering for Image Semantic Segment...

引用

26th IEEE conference on computer vision and pattern recognition (CVPR)

作者： Liu, Yang Liu, Jing Li, Zechao Tang, Jinhui Lu, Hanqing Chinese Acad Sci Inst Automat NLPR Beijing 100190 Peoples R China Nanjing Univ Sci & Tech Sch Comp Sci Beijing 210044 Peoples R China

ISBN: (纸本)9780769549897

In this paper, we propose a novel Weakly-Supervised Dual Clustering (WSDC) approach for image semantic segmentation with image-level labels, i.e., collaboratively performing image segmentation and tag alignment with those regions. the proposed approach is motivated from the observation that superpixels belonging to an object class usually exist across multiple images and hence can be gathered via the idea of clustering. In WSDC, spectral clustering is adopted to cluster the superpixels obtained from a set of over-segmented images. At the same time, a linear transformation between features and labels as a kind of discriminative clustering is learned to select the discriminative features among different classes. the both clustering outputs should be consistent as much as possible. Besides, weakly-supervised constraints from image-level labels are imposed to restrict the labeling of superpixels. Finally, the non-convex and non-smooth objective function are efficiently optimized using an iterative CCCP procedure. Extensive experiments conducted on MSRC and LabelMe datasets demonstrate the encouraging performance of our method in comparison with some state-of-the-arts.

关键词： image segmentation pattern clustering

来源：评论

学校读者我要写书评

暂无评论

Centerline Extraction of Line Structured Light in 3D Reconstruction 7

Centerline Extraction of Line Structured Light in 3D Reconst...

引用

7th International conference on Electrical, Mechanical and computer Engineering, ICEMCE 2023

作者： Zhang, Ji Wuhan Institute of Technology Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan China

ISBN: (纸本)9798350382877

At present, 3D reconstruction of binocular vision is a hot topic in the field of computer vision, and the extraction of laser fringe centers in line structured light images is a crucial step. In order to obtain the feature point set between the images, it is necessary to extract the centerline of the linear structured light bands. Firstly, through image preprocessing, perform image stereo correction and image Gaussian filtering, and adaptive threshold segmentation algorithm is used to segment the stripe area of the line structured light, and the image thinning algorithm is used to extract the initial centerline of the line structured light. Finally, the point set is constructed and the initial centerline is optimized twice by the gray-scale centroid method, and the centerline of the linear structured light stripe is accurately extracted. the results show that, compared with the Steger algorithm and the skeleton thinning method, the proposed method extracts the centerlines of the linear structured light stripes with higher accuracy. © 2023 IEEE.

关键词： Binocular vision

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：