检索结果-内蒙古大学图书馆

Deep convolution neural networks cascaded improved boosted forest for pedestrian detection

Journal of computers (Taiwan) 2018年第5期29卷 15-28页

作者： Xu, Zhi-Tong Luo, Yan-Min Liu, Pei-Zhong Du, Yong-Zhao College of Computer Science and Technology Huaqiao University Xiamen361021 China Key Laboratory for Computer Vision and Pattern Recognition of Xiamen City Huaqiao University Xiamen361021 China College of Engineering Huaqiao University Quanzhou362000 China

Due to the resolution of small size pedestrian is relatively low, and the hard negative background is very similar to people, therefore, detecting small size pedestrian or detecting pedestrian from hard negative background still a challenging problem in computer vision. In order to effectively address these problem, we propose a novel deep convolution neural networks, and cascade an improved boosted forest classifier method to detect pedestrian. Firstly, by using selective search method to propose pedestrian candidate boxes with confidence scores for utmost retaining image resolution;then, based on these proposed confidence values, adopting convolution neural network model to extract candidate regions feature maps;finally, we improve the boosted forest classifier and cascade it to classify candidate boxes for achieving efficiently pedestrian detection. Extensive experiments on Caltech and KITTI benchmarks demonstrate the proposed method outperforms the state-of-the-art, achieves promising precision on KITTI and the lowest miss rate of 11.53% on Caltech, outperforming the second best method (CompACT-Deep) by 0.17%. © 2018 computer Society of the Republic of China. All rights reserved.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results

arXiv

引用

arXiv 2022年

作者： Guo, Yulan Wang, Longguang Wang, Yingqian Li, Juncheng Gu, Shuhang Timofte, Radu Chen, Liangyu Chu, Xiaojie Yu, Wenqing Jin, Kai Wei, Zeqiang Guo, Sha Yang, Angulia Zhou, Xiuzhuang Guo, Guodong Xiao, Huaxin Yan, Shen Liu, Yuxiang Cai, Hanxiao Dai, Bin Peng, Feiyue Cao, Pu Nie, Yang Yang, Lu Song, Qing Hu, Xiaotao Xu, Jun Xu, Mai Jing, Junpeng Deng, Xin Xing, Qunliang Qiao, Minglang Guan, Zhenyu Guo, Wenlong Peng, Chenxu Chen, Zan Chen, Junyang Li, Hao Chen, Junbin Li, Weijie Yang, Zhijing Li, Gen Li, Aijin Sun, Lei Zhang, Dafeng Liu, Shizhuo Zhang, Jiangtao Qu, Yanyun Yang, Hao-Hsiang Huang, Zhi-Kai Chen, Wei-Ting Chang, Hua-En Kuo, Sy-Yen Liang, Qiaohui Lin, Jianxin Wang, Yijun Yin, Lianying Zhang, Rongju Zhao, Wei Xiao, Peng Xu, Rongjian Zhang, Zhilu Zuo, Wangmeng Guo, Hansheng Gao, Guangwei Zeng, Tieyong Kim, Joohyeok Kim, HyeonA Park, Eunpil Sim, Jae-Young Pi, Huicheng Zhang, Shunli Zhai, Jucai Zeng, Pengcheng Liu, Yang Ma, Chihao Huang, Yulin Chen, Junying National University of Defense Technology China The Chinese University of Hong Kong Hong Kong The University of Sydney Australia University of Würzburg ETH Zürich Switzerland MEGVII Technology China Peking University China Bigo Technology Pte. Ltd Singapore Smart Healthcare Innovation Lab Beijing University of Posts and Telecommunications China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Head of Institute of Deep Learning Baidu Research College of Systems Engineering National University of Defense Technology China College of Liberal Arts and Sciences National University of Defense Technology China Pattern Recognition and Intelligent Vision Lab Beijing University of Posts and Telecommunications China College of Computer Science Nankai University Tianjin China School of Statistics and Data Science Nankai University Tianjin Singapore Beihang University China Zhejiang University of Technology China Guangdong University of Technology China Tencent OVBU SRC-B Xiamen University China Department of Electrical Engineering National Taiwan University Taiwan Graduate Institute of Electronics Engineering National Taiwan University Taiwan College of Computer Science and Electronic Engineering Hunan University China Harbin Institude of Technology China The Chinese University of Hong Kong Hong Kong Nanjing University of Posts and Telecommunications China Department of Electrical Engineering Ulsan National Institute of Science and Technology Korea Republic of Graduate School of Artificial Intelligence Ulsan National Institute of Science and Technology Korea Republic of Beijing Jiaotong University China City University of Hong Kong Hong Kong South China University of Technology China

In this paper, we summarize the 1st NTIRE challenge on stereo image super-resolution (restoration of rich details in a pair of low-resolution stereo images) with a focus on new solutions and results. This challenge has 1 track aiming at the stereo image super-resolution problem under a standard bicubic degradation. In total, 238 participants were successfully registered, and 21 teams competed in the final testing phase. Among those participants, 20 teams successfully submitted results with PSNR (RGB) scores better than the baseline. This challenge establishes a new benchmark for stereo image SR. Copyright © 2022, The Authors. All rights reserved.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

ISI at the Sigmorphon 2017 shared task on morphological reinflection

ISI at the Sigmorphon 2017 shared task on morphological rein...

引用

2017 CoNLL SIGMORPHON Shared Task: Universal Morphological Reinflection, CoNLL 2017

作者： Chakrabarty, Abhisek Garain, Utpal Computer Vision and Pattern Recognition Unit Indian Statistical Institute 203 B.T. Road Kolkata700108 India

ISBN: (纸本)9781945626692

We present a system for morphological reinflection based on the LSTM model. Given an input word and morphosyntactic descriptions, the problem is to classify the proper edit tree that, applied on the input word, produces the target form. The proposed method does not require human defined features and it is language independent also. Currently, we evaluate our system only for task 1 without using any external data. From the test set results, it is found that the proposed model beats the baseline on 15 out of the 52 languages in high resource scenario. But its performance is poor when the training set size is medium or low. © 2017 Association for Computational Linguistics.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Efficient Audio-Visual Speaker recognition via Deep Heterogeneous Feature Fusion 12th

Efficient Audio-Visual Speaker Recognition via Deep Heteroge...

引用

12th Chinese Conference on Biometric recognition, CCBR 2017

作者： Liu, Yu-Hang Liu, Xin Fan, Wentao Zhong, Bineng Du, Ji-Xiang Department of Computer Science Huaqiao University Xiamen361021 China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University Xiamen361021 China

ISBN: (纸本)9783319699226

Audio-visual speaker recognition (AVSR) has long been an active research area primarily due to its complementary information for reliable access control in biometric system, and it is a challenging problem mainly attributes to its multimodal nature. In this paper, we present an efficient audio-visual speaker recognition approach via deep heterogeneous feature fusion. First, we exploit a dual-branch deep convolutional neural networks (CNN) learning framework to extract and fuse the high-level semantic features of face and audio data. Further, by considering the temporal dependency of audio-visual data, we embed the fused features into a bidirectional Long Short-Term Memory (LSTM) networks to produce the recognition result, though which the speakers acquired under different challenging conditions can be well identified. The experimental results have demonstrated the efficiency of our proposed approach in both audio-visual feature fusion and speaker recognition. © 2017, Springer International Publishing AG.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Preface

Advances in Intelligent Systems and Computing

引用

Advances in Intelligent Systems and Computing 2020年 1022 AISC卷 v-vi页

作者： Chaudhuri, Bidyut B. Nakagawa, Masaki Khanna, Pritee Kumar, Sanjeev Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Techno India University Kolkata India Department of Advanced Information Technology and Computer Sciences Tokyo Institute of Agriculture and Technology Koganei Tokyo Japan Department of Computer Science Indian Institute of Information Technology Design and Manufacturing Jabalpur Jabalpur Madhya Pradesh India Department of Mathematics Indian Institute of Technology Roorkee Roorkee Uttarakhand India

来源：评论

学校读者我要写书评

暂无评论

CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing

arXiv

引用

arXiv 2019年

作者： Zhang, Shifeng Liu, Ajian Wan, Jun Liang, Yanyan Guo, Guogong Escalera, Sergio Escalante, Hugo Jair Li, Stan Z. National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Macau University of Science and Technology Macau China Institute of Deep Learning Baidu Research and National Engineering Laboratory for Deep Learning Technology and Application Universitat de Barcelona Computer Vision Center Barcelona Catalonia Instituto Nacional de Astrofsica Ptica y Electrnica Puebla72840 Mexico

Face anti-spoofing is essential to prevent face recognition systems from a security breach. Much of the progresses have been made by the availability of face anti-spoofing benchmark datasets in recent years. However, existing face antispoofing benchmarks have limited number of subjects (≤170) and modalities (≤2), which hinder the further development of the academic community. To facilitate face anti-spoofing research, we introduce a large-scale multi-modal dataset, namely CASIASURF, which is the largest publicly available dataset for face antispoofing in terms of both subjects and modalities. Specifically, it consists of 1;000 subjects with 21;000 videos and each sample has 3 modalities (i.e., RGB, Depth and IR). We also provide comprehensive evaluation metrics, diverse evaluation protocols, training/validation/testing subsets and a measurement tool, developing a new benchmark for face anti-spoofing. Moreover, we present a novel multi-modal multi-scale fusion method as a strong baseline, which performs feature re-weighting to select the more informative channel features while suppressing the less useful ones for each modality across different scales. Extensive experiments have been conducted on the proposed dataset to verify its significance and generalization capability. The dataset is available at http://***/***/chalearnfacespoofingattackdete/. Copyright © 2019, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and recognition — RRC-MLT-2019

ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Te...

引用

International Conference on Document Analysis and recognition

作者： Nibal Nayef Yash Patel Michal Busta Pinaki Nath Chowdhury Dimosthenis Karatzas Wafa Khlif Jiri Matas Umapada Pal Jean-Christophe Burie Cheng-lin Liu Jean-Marc Ogier no affiliation The Robotics Institute Carnegie Mellon Universiry Pittsburgh USA Department of Cybernetics Czech Technical University Prague Czech Republic CVPR unit Indian Statistical Institute India Computer Vision Center Universitat Autònoma de Barcelona Spain L3i Laboratory University of La Rochelle France National Laboratory of Pattern Recognition Institute of Automation of Chinese Academy of Sciences China

With the growing cosmopolitan culture of modern cities, the need of robust Multi-Lingual scene Text (MLT) detection and recognition systems has never been more immense. With the goal to systematically benchmark and push the state-of-the-art forward, the proposed competition builds on top of the RRC-MLT-2017 with an additional end-to-end task, an additional language in the real images dataset, a large scale multi-lingual synthetic dataset to assist the training, and a baseline End-to-End recognition method. The real dataset consists of 20,000 images containing text from 10 languages. The challenge has 4 tasks covering various aspects of multi-lingual scene text: (a) text detection, (b) cropped word script classification, (c) joint text detection and script classification and (d) end-to-end detection and recognition. In total, the competition received 60 submissions from the research and industrial communities. This paper presents the dataset, the tasks and the findings of the presented RRC-MLT-2019 challenge.

关键词： Task analysis Text recognition Training Benchmark testing Protocols Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

ICDAR2019 Robust reading challenge on multi-lingual scene text detection and recognition – RRC-MLT-2019

arXiv

引用

arXiv 2019年

作者： Nayef, Nibal Patel, Yash Busta, Michal Chowdhury, Pinaki Nath Karatzas, Dimosthenis Khlif, Wafa Matas, Jiri Pal, Umapada Burie, Jean-Christophe Liu, Cheng-lin Ogier, Jean-Marc L3i Laboratory University of La Rochelle France Computer Vision Center Universitat Autònoma de Barcelona Spain CVPR unit Indian Statistical Institute India Robotics Institute Carnegie Mellon Universiry Pittsburgh United States Center for Machine Perception Department of Cybernetics Czech Technical University Prague Czech Republic National Laboratory of Pattern Recognition Institute of Automation of Chinese Academy of Sciences China

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

More Realistic and Efficient Face-Based Mobile Authentication using CNNs

More Realistic and Efficient Face-Based Mobile Authenticatio...

引用

International Joint Conference on Neural Networks

作者： Abhijit Das Abira Sengupta Muhammad Saqib Umapada Pal Michael Blumenstein Center for Artificial Intelligence School of Software University of Technology Sydney Australia Department of Computer Science Kalyani Government Engineering College Kalyani India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

In this work, we propose a more realistic and efficient face-based mobile authentication technique using CNNs. This paper discusses and explores an inevitable problem of using face images for mobile authentication, taken from varying distances with a front/selfie camera of the mobile phone. Incidentally, once an individual comes towards a certain distance from the camera, the face images get large and appear over-sized. Simultaneously sharp features of some portions of the face, such as forehead, cheek, and chin are changed completely. As a result, the face features change and the impact increases exponentially once the individual crosses a certain distance and gradually approaches towards the front camera. This work proposes a solution (achieving better accuracy and facial features, whereby face images were cropped and aligned around its close bounding box) to mitigate the aforementioned identified gap. The work investigated different frontier face detection and recognition techniques to justify the proposed solution. Among all the employed methods evaluated, CNNs worked best. For a quantitative comparison of the proposed method, manually cropped face images/annotations of the face images along with their close boundary were prepared. In turn, we have developed a database considering the above-mentioned scenario for 40 individuals, which will be publicly available for academic research purposes. The experimental results achieved indicate a successful implementation of the proposed method and the performance of the proposed technique is also found to be superior in comparison to the existing state-of-the-art.

关键词： Face Cameras Feature extraction Authentication Face recognition Optical distortion Face detection

来源：评论

学校读者我要写书评

暂无评论

Music Instrument Identification Based on a 2-D Representation

Music Instrument Identification Based on a 2-D Representatio...

引用

International Conference on Electrical, Electronics, Communication, computer and Optimization Techniques (ICEECCOT)

作者： Alekhya Ghosh Arghadeep Pal Dibakar Sil Sarbani Palit Electronics and Communication Engineering IRPEL University of Calcutta Kolkata India Electronics and Communication Engineering National Institute of Technology Durgapur India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

ISBN: (数字)9781538651308

ISBN: (纸本)9781538651315

Automatic recognition of musical instruments has been a great problem in the field of digital signal processing. In this work a novel, compact set of features obtained by transforming a music signal to the spatial domain is introduced with promising results. Preliminary results on a popular music database, presented in terms of precision, recall and identification accuracy, are highly encouraging. The best result comprises an accuracy of 84.02% by Decision Tree (DT) for a set of 9 instruments belonging to different families. The accuracy for predicting the instrument family 96.07% for string family and for wind instrument the overall prediction accuracy is 90.78%. Further inclusion of some other features from some available works are also checked leading to slight increase in the accuracy. The obtained results are also compared with the result predicted by the VGG - 16 network on the same dataset. The feature set containing 8 features that introduces less computational complexity compared to available works, may be considered as a major contribution. The comparison shows, we can replicate nearly accurate classification through our proposed method in less amount of time than deep neural architecture.

关键词： Instruments Decision trees Forestry Feature extraction Timbre Matrix converters

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：