检索结果-内蒙古大学图书馆

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

作者： Lin, Jin-Fu Lin, Yen-Liang King, Erh-Kan Su, Hung-Ting Hsu, Winston H. Natl Taiwan Univ Taipei Taiwan GE Global Res Niskayuna NY USA

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

Existing fine-grained object recognition methods often require high-resolution images to better discriminate the subordinate classes. However, this assumption does not always hold in current surveillance systems, where the distinguished parts may not be clearly presented. Besides, data insufficiency and class imbalance make the problem even more challenging. In this paper, we leverage high-resolution images collected from Internet to improve the vehicle recognition in the surveillance environments. A cross-domain hallucination network is proposed to minimize the domain discrepancy and enhance the quality of low-resolution surveillance images. To better align the cross-domain features and boost the recognition performance, we extend the original framework to part-based hallucination networks, where the parts are automatically extracted based on the maximum responses from the convolution filters. We evaluate our method on a public surveillance vehicle dataset (BoxCars21k). Experimental results demonstrate that our approach outperforms the state-of-the-art methods.

关键词： cross-domain hallucination fine-grained classification

来源：评论

学校读者我要写书评

暂无评论

IFQ-Net: Integrated Fixed-point Quantization Networks for Embedded vision 31

IFQ-Net: Integrated Fixed-point Quantization Networks for Em...

引用

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

作者： Gao, Hongxing Tao, Wei Wen, Dongchao Chen, Tse-Wei Osa, Kinya Kato, Masami Canon Informat Technol Beijing Co LTD Beijing Peoples R China Canon Inc Device Technol Dev Headquarters Tokyo Japan

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

Deploying deep models on embedded devices has been a challenging problem since the great success of deep learning based networks. Fixed-point networks, which represent their data with low bits fixed-point and thus give remarkable savings on memory usage, are generally preferred. Even though current fixed-point networks employ relative low bits (e.g. 8-bits), the memory saving is far from enough for the embedded devices. On the other hand, quantization deep networks, for example XNOR-Net and HWGQ-Net, quantize the data into 1 or 2 bits resulting in more significant memory savings but still contain lots of floating-point data. In this paper, we propose a fixed-point network for embedded vision tasks through converting the floating-point data in a quantization network into fixed-point. Furthermore, to overcome the data loss caused by the conversion, we propose to compose floating-point data operations across multiple layers (e.g. convolution, batch normalization and quantization layers) and convert them into fixedpoint. We name the fixed-point network obtained through such integrated conversion as Integrated Fixed-point Quantization Networks (IFQ-Net). We demonstrate that our IFQ-Net gives 2.16x and 18x more savings on model size and runtime feature map memory respectively with similar accuracy on ImageNet. Furthermore, based on YOLOv2, we design IFQ-Tinier-YOLO face detector which is a fixed-point network with 256x reduction in model size (246k Bytes) than Tiny-YOLO. We illustrate the promising performance of our face detector in terms of detection rate on Face Detection Data Set and Bencmark (FDDB) and qualitative results of detecting small faces of Wider Face dataset.

关键词： Quantization (signal) Convolution Face Computational modeling Task analysis Detectors Runtime

来源：评论

学校读者我要写书评

暂无评论

SkeletonNet: Shape Pixel to Skeleton Pixel

SkeletonNet: Shape Pixel to Skeleton Pixel

引用

ieee computer society conference on computer vision and pattern recognition Workshops (cvprW)

作者： Sabari Nathan Priya Kansal Couger Inc.

ISBN: (数字)9781728125060

ISBN: (纸本)9781728125077

Deep Learning for Geometric Shape Understating has organized a challenge for extracting different kinds of skeletons from the images of different objects. This competition is organized in association with cvpr 2019. There are three different tracks of this competition. The present manuscript describes the method used to train the model for the dataset provided in the first track. The first track aims to extract skeleton pixels from the shape pixels of 89 different objects. For the purpose of extracting the skeleton, a U-net model which is comprised of an encoder-decoder structure has been used. In our proposed architecture, unlike the plain decoder in the traditional U net, we have designed the decoder in the format of HED architecture, wherein we have introduced 4 side layers and fused them to one dilation convolutional layer to connect the broken links of the skeleton. Our proposed architecture achieved the F1 score of 0.77 on test data.

关键词： Skeleton Decoding Training computer architecture Image edge detection Task analysis computer vision

来源：评论

学校读者我要写书评

暂无评论

SINT++: Robust Visual Tracking via Adversarial Positive Instance Generation 31

SINT++: Robust Visual Tracking via Adversarial Positive Inst...

引用

31st Meeting of the ieee/CVF conference on computer vision and pattern recognition, cvpr 2018

作者： Wang, Xiao Li, Chenglong Luo, Bin Tang, Jin School of Computer Science and Technology Anhui University Hefei230601 China

ISBN: (纸本)9781538664209

Existing visual trackers are easily disturbed by occlusion, blur and large deformation. We think the performance of existing visual trackers may be limited due to the following issues: I) Adopting the dense sampling strategy to generate positive examples will make them less diverse;ii) The training data with different challenging factors are limited, even through collecting large training dataset. Collecting even larger training dataset is the most intuitive paradigm, but it may still can not cover all situations and the positive samples are still monotonous. In this paper, we propose to generate hard positive samples via adversarial learning for visual tracking. Specifically speaking, we assume the target objects all lie on a manifold, hence, we introduce the positive samples generation network (PSGN) to sampling massive diverse training data through traversing over the constructed target object manifold. The generated diverse target object images can enrich the training dataset and enhance the robustness of visual trackers. To make the tracker more robust to occlusion, we adopt the hard positive transformation network (HPTN) which can generate hard samples for tracking algorithm to recognize. We train this network with deep reinforcement learning to automatically occlude the target object with a negative patch. Based on the generated hard positive samples, we train a Siamese network for visual tracking and our experiments validate the effectiveness of the introduced algorithm. The project page of this paper can be found from the website1. © 2018 ieee.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal 31

Stacked Conditional Generative Adversarial Networks for Join...

引用

31st Meeting of the ieee/CVF conference on computer vision and pattern recognition, cvpr 2018

作者： Wang, Jifeng Li, Xiang Yang, Jian DeepInsight at PCALab Nanjing University of Science and Technology China Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

ISBN: (纸本)9781538664209

Understanding shadows from a single image consists of two types of task in previous studies, containing shadow detection and shadow removal. In this paper, we present a multi-task perspective, which is not embraced by any existing work, to jointly learn both detection and removal in an end-to-end fashion that aims at enjoying the mutually improved benefits from each other. Our framework is based on a novel STacked Conditional Generative Adversarial Network (ST-CGAN), which is composed of two stacked CGANs, each with a generator and a discriminator. Specifically, a shadow image is fed into the first generator which produces a shadow detection mask. That shadow image, concatenated with its predicted mask, goes through the second generator in order to recover its shadow-free image consequently. In addition, the two corresponding discriminators are very likely to model higher level relationships and global scene characteristics for the detected shadow region and reconstruction via removing shadows, respectively. More importantly, for multi-task learning, our design of stacked paradigm provides a novel view which is notably different from the commonly used one as the multi-branch version. To fully evaluate the performance of our proposed framework, we construct the first large-scale benchmark with 1870 image triplets (shadow image, shadow mask image, and shadow-free image) under 135 scenes. Extensive experimental results consistently show the advantages of STC-GAN over several representative state-of-the-art methods on two large-scale publicly available datasets and our newly released one. © 2018 ieee.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

In Defense of Active Part Selection for Fine-Grained Classification

引用

pattern recognition and Image Analysis 2018年第4期28卷 658-663页

作者： Korsch, D. Denzler, J. Computer Vision Group Friedrich Schiller University Jena Jena Germany

Fine-grained classification is a recognition task where subtle differences distinguish between different classes. To tackle this classification problem, part-based classification methods are mostly used. Partbased methods learn an algorithm to detect parts of the observed object and extract local part features for the detected part regions. In this paper we show that not all extracted part features are always useful for the classification. Furthermore, given a part selection algorithm that actively selects parts for the classification we estimate the upper bound for the fine-grained recognition performance. This upper bound lies way above the current state-of-the-art recognition performances which shows the need for such an active part selection method. Though we do not present such an active part selection algorithm in this work, we propose a novel method that is required by active part selection and enables sequential part-based classification. This method uses a support vector machine (SVM) ensemble and allows to classify an image based on arbitrary number of part features. Additionally, the training time of our method does not increase with the amount of possible part features. This fact allows to extend the SVM ensemble with an active part selection component that operates on a large amount of part feature proposals without suffering from increasing training time. © 2018, Pleiades Publishing, Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

3D Cell Nuclear Morphology: Microscopy Imaging Dataset and Voxel-Based Morphometry Classification Results 31

3D Cell Nuclear Morphology: Microscopy Imaging Dataset and V...

引用

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

作者： Kalinin, Alexandr A. Allyn-Feuer, Ari Ade, Alex Fon, Gordon-Victor Meixner, Walter Dilworth, David de Wet, Jeffrey R. Higgins, Gerald A. Zheng, Gen Creekmore, Amy Wiley, John W. Verdone, James E. Veltri, Robert W. Pienta, Kenneth J. Coffey, Donald S. Athey, Brian D. Dinov, Ivo D. Univ Michigan Sch Med Dept Computat Med & Bioinformat Ann Arbor MI 48109 USA Univ Michigan Sch Nursing SOCR Hlth Behav & Biol Sci Ann Arbor MI 48109 USA Univ Michigan Sch Med Dept Internal Med Div Gastroenterol Ann Arbor MI 48109 USA Johns Hopkins Univ Dept Urol James Buchanan Brady Urol Inst Baltimore MD 21218 USA Univ Michigan Michigan Inst Data Sci MIDAS Ann Arbor MI 48109 USA

ISBN: (数字)9781538661000

ISBN: (纸本)9781538661000

Cell deformation is regulated by complex underlying biological mechanisms associated with spatial and temporal morphological changes in the nucleus that are related to cell differentiation, development, proliferation, and disease. Thus, quantitative analysis of changes in size and shape of nuclear structures in 3D microscopic images is important not only for investigating nuclear organization, but also for detecting and treating pathological conditions such as cancer. While many efforts have been made to develop cell and nuclear shape characteristics in 2D or pseudo-3D, several studies have suggested that 3D morphometric measures provide better results for nuclear shape description and discrimination. A few methods have been proposed to classify cell and nuclear morphological phenotypes in 3D, however, there is a lack of publicly available 3D data for the evaluation and comparison of such algorithms. This limitation becomes of great importance when the ability to evaluate different approaches on benchmark data is needed for better dissemination of the current state of the art methods for bioimage analysis. To address this problem, we present a dataset containing two different cell collections, including original 3D microscopic images of cell nuclei and nucleoli. In addition, we perform a baseline evaluation of a number of popular classification algorithms using 2D and 3D voxel-based morphometric measures. To account for batch effects, while enabling calculations of AU-ROC and AUPR performance metrics, we propose a specific cross-validation scheme that we compare with commonly used k-fold cross-validation. Original and derived imaging data are made publicly available on the project webpage: http://***/projects/3d-cell-morphometry/***.

关键词： Three-dimensional displays computer architecture Image segmentation Microprocessors Microscopy Two dimensional displays Morphology

来源：评论

学校读者我要写书评

暂无评论

Occluded Pedestrian Detection Through Guided Attention in CNNs 31

Occluded Pedestrian Detection Through Guided Attention in CN...

引用

ieee/CVF conference on computer vision and pattern recognition

作者： Shanshan Zhang Jian Yang Bernt Schiele Ministry of Education Key Lab of Intelligent Perception and Systems for High-Dimensional Information Jiangsu Key Lab of Image and Video Understanding for Social Security Nanjing University of Science and Technology China Saarland Informatics Campus Max Planck Institute for Informatics Germany

ISBN: (纸本)9781538664216;9781538664209

Pedestrian detection has progressed significantly in the last years. However, occluded people are notoriously hard to detect, as their appearance varies substantially depending on a wide range of occlusion patterns. In this paper, we aim to propose a simple and compact method based on the FasterRCNN architecture for occluded pedestrian detection. We start with interpreting CNN channel features of a pedestrian detector, and we find that different channels activate responses for different body parts respectively. These findings motivate us to employ an attention mechanism across channels to represent various occlusion patterns in one single model, as each occlusion pattern can be formulated as some specific combination of body parts. Therefore, an attention network with self or external guidances is proposed as an add-on to the baseline FasterRCNN detector. When evaluating on the heavy occlusion subset, we achieve a significant improvement of 8pp to the baseline FasterRCNN detector on CityPersons and on Caltech we outperform the state-of-the-art method by 4pp.

关键词： Detectors Feature extraction computer architecture Object detection Training Body regions Correlation

来源：评论

学校读者我要写书评

暂无评论

Special Section Guest Editorial: Image and Video Analysis, Detection and recognition

引用

Journal of Electronic Imaging 2018年第5期27卷

作者： Ardizzone, Edoardo Celebi, M. Emre Palermo Italy University of Central Arkansas Department of Computer Science ConwayAR United States

This editorial summarizes the JEI Special Section on Image and Video Analysis, Detection and recognition.

关键词： Image analysis Video Image segmentation Image processing Machine learning Video surveillance computer engineering computer science Convolutional neural networks Motion models

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2018 Challenge on Single Image Super-Resolution: Methods and Results 31

NTIRE 2018 Challenge on Single Image Super-Resolution: Metho...

引用

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

作者： Timofte, Radu Gu, Shuhang Wu, Jiqing Van Gool, Luc Zhang, Lei Yang, Ming-Hsuan Haris, Muhammad Shakhnarovich, Greg Ukita, Norimichi Hu, Shijia Bei, Yijie Hui, Zheng Jiang, Xiao Gu, Yanan Liu, Jie Wang, Yifan Perazzi, Federico McWilliams, Brian Sorkin-Hornung, Alexander Sorkine-Hornung, Olga Schroers, Christopher Yu, Jiahui Fan, Yuchen Yang, Jianchao Xu, Ning Wang, Zhaowen Wang, Xinchao Huang, Thomas S. Wang, Xintao Yu, Ke Hui, Tak-Wai Dong, Chao Lin, Liang Loy, Chen Change Park, Dongwon Kim, Kwanyoung Chun, Se Young Zhang, Kai Liu, Pengjv Zuo, Wangmeng Guo, Shi Liu, Jiye Xu, Jinchang Liu, Yijiao Xiong, Fengye Dong, Yuan Bai, Hongliang Damian, Alexandru Ravi, Nikhil Menon, Sachit Rudin, Cynthia Seo, Junghoon Jeon, Taegyun Koo, Jamyoung Jeon, Seunghyun Kim, Soo Ye Choi, Jae-Seok Ki, Sehwan Seo, Soomin Sim, Hyeonjun Kim, Saehun Kim, Munchurl Chen, Rong Zeng, Kun Guo, Jinkang Qu, Yanyun Li, Cuihua Ahn, Namhyuk Kang, Byungkon Sohn, Kyung-Ah Yuan, Yuan Zhang, Jiawei Pang, Jiahao Xu, Xiangyu Zhao, Yan Deng, Wei Ul Hussain, Sibt Aadil, Muneeb Rahim, Rafia Cai, Xiaowang Huang, Fang Xu, Yueshu Michelini, Pablo Navarrete Zhu, Dan Liu, Hanwen Kim, Jun-Hyuk Lee, Jong-Seok Huang, Yiwen Qiu, Ming Jing, Liting Zeng, Jiehang Wang, Ying Sharma, Manoj Mukhopadhyay, Rudrabha Upadhyay, Avinash Koundinya, Sriharsha Shukla, Ankit Chaudhury, Santanu Zhang, Zhe Hu, Yu Hen Fu, Lingzhi Swiss Fed Inst Technol Comp Vis Lab Zurich Switzerland Merantix Berlin Germany Katholieke Univ Leuven ESAT Leuven Belgium Hong Kong Polytech Univ Hong Kong Peoples R China Univ Calif Merced Merced CA USA Toyota Technol Inst Nagoya Aichi Japan TTI Chicago Chicago IL USA Duke Univ Durham NC USA Xidian Univ Sch Elect Engn Xian Shaanxi Peoples R China Disney Res Zurich Switzerland Swiss Fed Inst Technol Zurich Switzerland Facebook Oculus Zurich Switzerland Univ Illinois Urbana IL USA Snap Inc Los Angeles CA USA Adobe Res San Jose CA USA Stevens Inst Technol Hoboken NJ 07030 USA Chinese Univ Hong Kong Hong Kong Peoples R China SenseTime Res Hong Kong Peoples R China Ulsan Natl Inst Sci & Technol Sch Elect & Comp Engn Ulsan South Korea Harbin Inst Technol Sch Comp Sci & Technol Harbin Heilongjiang Peoples R China Beijing Univ Posts & Telecommun Beijing Peoples R China Beijing Faceall Technol Co Ltd Beijing Peoples R China Satrec Initiat R&D Ctr Daejeon South Korea Korea Adv Inst Sci & Technol Daejeon South Korea Xiamen Univ Xiamen Peoples R China Ajou Univ Suwon South Korea Univ Alberta Elect & Comp Engn Edmonton AB Canada Fuzhou Univ Fuzhou Fujian Peoples R China Natl Univ Comp & Emerging Sci Islamabad Pakistan BOE Technol Grp Co Ltd Beijing Peoples R China Yonsei Univ Seoul South Korea Wenhua Coll Wuhan Hubei Peoples R China Xiamen Univ Software Sch Xiamen Peoples R China CSIR CEERI Pilani Rajasthan India Univ Wisconsin Dept Elect & Comp Engn 1415 Johnson Dr Madison WI 53706 USA Xi An Jiao Tong Univ Sch Elect & Informat Engn Inst Integrated Automat MOE KLINNS Lab Xian Shaanxi Peoples R China

ISBN: (纸本)9781538661000

This paper reviews the 2nd NTIRE challenge on single image super-resolution (restoration of rich details in a low resolution image) with focus on proposed solutions and results. The challenge had 4 tracks. Track 1 employed the standard bicubic downscaling setup, while Tracks 2, 3 and 4 had realistic unknown downgrading operators simulating camera image acquisition pipeline. The operators were learnable through provided pairs of low and high resolution train images. The tracks had 145, 114, 101, and 113 registered participants, resp., and 31 teams competed in the final testing phase. They gauge the state-of-the-art in single image super-resolution.

关键词： Image resolution Degradation Training Runtime computer architecture Testing Tracking

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：