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： Zhou, Zhen Huang, Yan Wang, Wei Wang, Liang Tan, Tieniu Natl Lab Pattern Recognit NLPR Ctr Res Intelligent Percept & Comp CRIPAC Beijing Peoples R China Chinese Acad Sci CASIA Inst Automat Ctr Excellence Brain Sci & Intelligence Technol C Beijing Peoples R China Univ Chinese Acad Sci UCAS Beijing Peoples R China

ISBN: (纸本)9781538604571

Surveillance cameras have been widely used in different scenes. Accordingly, a demanding need is to recognize a person under different cameras, which is called person re-identification. this topic has gained increasing interests in computer vision recently. However, less attention has been paid to video-based approaches, compared with image-based ones. Two steps are usually involved in previous approaches, namely feature learning and metric learning. But most of the existing approaches only focus on either feature learning or metric learning. Meanwhile, many of them do not take full use of the temporal and spatial information. In this paper, we concentrate on video-based person re-identification and build an end-to-end deep neural network architecture to jointly learn features and metrics. the proposed method can automatically pick out the most discriminative frames in a given video by a temporal attention model. Moreover, it integrates the surrounding information at each location by a spatial recurrent model when measuring the similarity with another pedestrian video. that is, our method handles spatial and temporal information simultaneously in a unified manner. the carefully designed experiments on three public datasets show the effectiveness of each component of the proposed deep network, performing better in comparison with the state-of-the-art methods.

关键词： Measurement Image sequences Feature extraction computer architecture computer vision Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Weighted-Entropy-based Quantization for Deep Neural Networks 30

Weighted-Entropy-based Quantization for Deep Neural Networks

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Park, Eunhyeok Ahn, Junwhan Yoo, Sungjoo Seoul Natl Univ Comp & Memory Architecture Lab Seoul South Korea Seoul Natl Univ Design Automat Lab Seoul South Korea

ISBN: (纸本)9781538604571

Quantization is considered as one of the most effective methods to optimize the inference cost of neural network models for their deployment to mobile and embedded systems, which have tight resource constraints. In such approaches, it is critical to provide low-cost quantization under a tight accuracy loss constraint (e.g., 1%). In this paper, we propose a novel method for quantizing weights and activations based on the concept of weighted entropy. Unlike recent work on binary-weight neural networks, our approach is multi-bit quantization, in which weights and activations can be quantized by any number of bits depending on the target accuracy. this facilitates much more flexible exploitation of accuracy-performance trade-off provided by different levels of quantization. Moreover, our scheme provides an automated quantization flow based on conventional training algorithms, which greatly reduces the design-time effort to quantize the network. According to our extensive evaluations based on practical neural network models for image classification (AlexNet, GoogLeNet and ResNet-50/101), object detection (R-FCN with ResNet-50), and language modeling (an LSTM network), our method achieves significant reductions in both the model size and the amount of computation with minimal accuracy loss. Also, compared to existing quantization schemes, ours provides higher accuracy with a similar resource constraint and requires much lower design effort.

关键词： Quantization model size Neural network design effort Activation Embedded systems Neural Networks (computer) Drill bits

来源：评论

学校读者我要写书评

暂无评论

A Deep Regression Architecture with Two-Stage Re-initialization for High Performance Facial Landmark Detection 30

A Deep Regression Architecture with Two-Stage Re-initializat...

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Lv, Jiangjing Shao, Xiaohu Xing, Junliang Cheng, Cheng Zhou, Xi Chinese Acad Sci Chongqing Inst Green & Intelligent Technol Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Chinese Acad Sci Inst Automat Beijing Peoples R China

ISBN: (纸本)9781538604571

Regression based facial landmark detection methods usually learns a series of regression functions to update the landmark positions from an initial estimation. Most of existing approaches focus on learning effective mapping functions with robust image features to improve performance. the approach to dealing with the initialization issue, however, receives relatively fewer attentions. In this paper, we present a deep regression architecture with two-stage re-initialization to explicitly deal with the initialization problem. At the global stage, given an image with a rough face detection result, the full face region is firstly re-initialized by a supervised spatial transformer network to a canonical shape state and then trained to regress a coarse landmark estimation. At the local stage, different face parts are further separately re-initialized to their own canonical shape states, followed by another regression subnetwork to get the final estimation. Our proposed deep architecture is trained from end to end and obtains promising results using different kinds of unstable initialization. It also achieves superior performances over many competing algorithms.

关键词： Face Shape computer architecture Robustness Detectors Machine learning

来源：评论

学校读者我要写书评

暂无评论

Binarized Mode Seeking for Scalable Visual pattern Discovery 30

Binarized Mode Seeking for Scalable Visual Pattern Discovery

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Zhang, Wei Cao, Xiaochun Wang, Rui Guo, Yuanfang Chen, Zhineng Chinese Acad Sci Inst Informat Engn SKLOIS Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China Chinese Acad Sci Inst Automat Beijing Peoples R China

ISBN: (纸本)9781538604571

this paper studies visual pattern discovery in large-scale image collections via binarized mode seeking, where images can only be represented as binary codes for efficient storage and computation. We address this problem from the perspective of binary space mode seeking. First, a binary mean shift (bMS) is proposed to discover frequent patterns via mode seeking directly in binary space. the binomial-based kernel and binary constraint are introduced for binarized analysis. Second, we further extend bMS to a more general form, namely contrastive binary mean shift (cbMS), which maximizes the contrastive density in binary space, for finding informative patterns that are both frequent and discriminative for the dataset. With the binarized algorithm and optimization, our methods demonstrate significant computation (50x) and storage (32x) improvement compared to standard techniques operating in Euclidean space, while the performance does not largely degenerate. Furthermore, cbMS discovers more informative patterns by suppressing low discriminative modes. We evaluate our methods on both annotated ILSVRC (1M images) and un-annotated blind Flickr (10M images) datasets with million scale images, which demonstrates both the scalability and effectiveness of our algorithms for discovering frequent and informative patterns in large scale collection.

关键词： Binary Scalability images binary code Dataset Euclidean space spatial mode image samples Visualization

来源：评论

学校读者我要写书评

暂无评论

Hardware-Efficient Guided Image Filtering For Multi-Label Problem 30

Hardware-Efficient Guided Image Filtering For Multi-Label Pr...

引用

30th ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Dai, Longquan Yuan, Mengke Li, Zechao Zhang, Xiaopeng Tang, Jinhui Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing Jiangsu Peoples R China Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing Peoples R China

ISBN: (纸本)9781538604571

the Guided Filter (GF) is well-known for its linear complexity. However, when filtering an image with an n-channel guidance, GF needs to invert an nxn matrix for each pixel. To the best of our knowledge existing matrix inverse algorithms are inefficient on current hardwares. this shortcoming limits applications of multichannel guidance in computation intensive system such as multi-label system. We need a new GF-like filter that can perform fast multichannel image guided filtering. Since the optimal linear complexity of GF cannot be minimized further, the only way thus is to bring all potentialities of current parallel computing hardwares into full play. In this paper we propose a hardware-efficient Guided Filter (HGF), which solves the efficiency problem of multichannel guided image filtering and yields competent results when applying it to multi-label problems with synthesized polynomial multichannel guidance. Specifically, in order to boost the filtering performance, HGF takes a new matrix inverse algorithm which only involves two hardware-efficient operations: element-wise arithmetic calculations and box filtering. In order to break the linear model restriction, HGF synthesizes a polynomial multichannel guidance to introduce nonlinearity. Benefiting from our polynomial guidance and hardware-efficient matrix inverse algorithm, HGF not only is more sensitive to the underlying structure of guidance but also achieves the fastest computing speed. Due to these merits, HGF obtains state-of-the-art results in terms of accuracy and efficiency in the computation intensive multi-label systems.

关键词： image filtering Guidance Interleukin-6 SOS1 gene HGF gene Hepatocyte Growth Factor Filtration Inverse matrix Filters arithmetic Economic Resources linear complexity

来源：评论

学校读者我要写书评

暂无评论

Distributed Multi-Target Tracking and Data Association in vision Networks

引用

ieee TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 2016年第7期38卷 1397-1397页

作者： Kamal, Ahmed T. Bappy, Jawadul H. Farrell, Jay A. Roy-Chowdhury, Amit K. Univ Calif Riverside Riverside CA 92521 USA

Distributed algorithms have recently gained immense popularity. With regards to computer vision applications, distributed multi-target tracking in a camera network is a fundamental problem. the goal is for all cameras to have accurate state estimates for all targets. Distributed estimation algorithms work by exchanging information between sensors that are communication neighbors. vision-based distributed multi-target state estimation has at least two characteristics that distinguishes it from other applications. First, cameras are directional sensors and often neighboring sensors may not be sensing the same targets, i.e., they are naive with respect to that target. Second, in the presence of clutter and multiple targets, each camera must solve a data association problem. this paper presents an information-weighted, consensus-based, distributed multi-target tracking algorithm referred to as the Multi-target Information Consensus (MTIC) algorithm that is designed to address both the naivety and the data association problems. It converges to the centralized minimum mean square error estimate. the proposed MTIC algorithm and its extensions to non-linear camera models, termed as the Extended MTIC (EMTIC), are robust to false measurements and limited resources like power, bandwidth and the realtime operational requirements. Simulation and experimental analysis are provided to support the theoretical results.

关键词： Consensus distributed tracking data association camera networks

来源：评论

学校读者我要写书评

暂无评论

Deep Residual Network with Enhanced Upscaling Module for Super-Resolution 31

Deep Residual Network with Enhanced Upscaling Module for Sup...

引用

ieee/CVF conference on computer vision and pattern recognition (cvpr)

作者： Kim, Jun-Hyuk Lee, Jong-Seok Yonsei Univ Sch Integrated Technol Seoul South Korea

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

Single image super-resolution (SR) have recently shown great performance thanks to the advances in deep learning. In the middle of the deep networks for SR, a part that increases image resolution is required, for which a sub-pixel convolution layer is known as an efficient way. However, we argue that the method has room for improvement, and propose an enhanced upscaling module (EUM), which achieves improvement by utilizing nonlinear operations and skip connections. Employing our proposed EUM, we propose a novel deep residual network for SR, called EUSR. Our proposed EUSR was ranked in the 9th place among 24 teams in terms of SSIM in track 1 of the NTIRE 2018 SR Challenge [25]. In addition, we experimentally show that EUSR has comparable performance on x2 and x4 SR for four benchmark datasets to the state-of-the-art methods, and outperforms them on a large scaling factor (x8).

关键词： Convolution Image resolution Feature extraction Training Image reconstruction computer vision Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Active Learning of Classifiers & Attributes via Relative Feedback

Simultaneous Active Learning of Classifiers & Attributes via...

引用

26th ieee conference on computer vision and pattern recognition (cvpr)

作者： Biswas, Arijit Parikh, Devi Univ Maryland College Pk MD 20742 USA Virginia Tech Blacksburg VA USA

ISBN: (纸本)9780769549897

Active learning provides useful tools to reduce annotation costs without compromising classifier performance. However it traditionally views the supervisor simply as a labeling machine. Recently a new interactive learning paradigm was introduced that allows the supervisor to additionally convey useful domain knowledge using attributes. the learner first conveys its belief about an actively chosen image e. g. "I think this is a forest, what do you think?". If the learner is wrong, the supervisor provides an explanation e. g. "No, this is too open to be a forest". With access to a pre-trained set of relative attribute predictors, the learner fetches all unlabeled images more open than the query image, and uses them as negative examples of forests to update its classifier this rich human-machine communication leads to better classification performance. In this work, we propose three improvements over this set-up. First, we incorporate a weighting scheme that instead of making a hard decision reasons about the likelihood of an image being a negative example. Second, we do away with pre-trained attributes and instead learn the attribute models on the fly, alleviating overhead and restrictions of a pre-determined attribute vocabulary. Finally, we propose an active learning framework that accounts for not just the label-but also the attributes-based feedback while selecting the next query image. We demonstrate significant improvement in classification accuracy on faces and shoes. We also collect and make available the largest relative attributes dataset containing 29 attributes of faces from 60 categories.

关键词： image retrieval interactive systems learning (artificial intelligence) man-machine systems pattern classification

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study of Optical Character recognition 29

A Comprehensive Study of Optical Character Recognition

引用

29th International conference on Mixed Design of Integrated Circuits and System (MIXDES)

作者： Raj, Ravi Kos, Andrzej AGH Univ Sci & Technol Fac Comp Sci Elect & Telecommun Al Adama Mickiewicza 30 PL-30059 Krakow Poland

ISBN: (数字)9788363578220

ISBN: (纸本)9781665461764

In recent decades recognition of characters has become a most important research topic for computer vision researchers or scientists. One of the major techniques for character recognition is optical character recognition (OCR) which plays a vital role in recent years in the development of various methodologies for the recognition of characters of several languages alphabets. Currently, OCR technology is utilized by most of the applications of scanning documents and makes them readable for the users such as google translate, which has been developed for translating the language from one language to the other language. But the rate of accuracy and timing to perform the specified task is still a problem. this paper presents a brief description of the OCR technology, the timeline of its development, some major applications of this technology, and its future perspective in our daily life. Moreover, this article provides an overview of this fascinating research topic for the early-stage researchers of computer vision.

关键词： OCR Artificial Intelligence computer vision pattern recognition Character recognition

来源：评论

学校读者我要写书评

暂无评论

An overview of robot vision

An overview of robot vision

引用

27th Southern African Universities Power Engineering conference (SAUPEC) / 11th Robotics and Mechatronics conference of South Africa (RobMech) / 29th Annual Symposium of pattern-recognition-Association-of-South-Africa (PRASA)

作者： van Eden, Beatrice Rosman, Benjamin CSIR Mobile Intelligent Autonomous Syst Pretoria South Africa Univ Witwatersrand Sch Comp Sci & Appl Math Johannesburg South Africa

ISBN: (纸本)9781728103693

Robot vision is an interdisciplinary field that deals with how robots can be made to gain high-level understanding from digital images or videos. Understanding an image at the pixel level often does not provide enough information for decision making and action taking. In this case, higher level semantic information that describes the image is required. this helps the robot to accomplish complex tasks that require visual understanding. For robots to add value they need to be sufficiently effective at executing tasks in different settings. Despite many impressive advances in robot vision, robots still lack the ability to function as humans do in complex environments. Importantly, this includes being able to interpret and understand the perceptual complexities of the world. Robot vision is dependant on ideas from both computer vision and machine learning. In this paper we provide a overview of the advances in these disciplines and how they contribute to robot vision.

关键词： Robot sensing systems Image classification Object recognition Object detection Visualization computer architecture

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：