检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Gu, Jinjin Cai, Haoming Chen, Haoyu Ye, Xiaoxing Ren, Jimmy S. Dong, Chao School of Electrical and Information Engineering University of Sydney Australia Chinese University of Hong Kong Shenzhen Hong Kong ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SenseTime Research Qing Yuan Research Institute Shanghai Jiao Tong University Shanghai China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Image quality assessment (IQA) is the key factor for the fast development of image restoration (IR) algorithms. The most recent perceptual IR algorithms based on generative adversarial networks (GANs) have brought in significant improvement on visual performance, but also pose great challenges for quantitative evaluation. Notably, we observe an increasing inconsistency between perceptual quality and the evaluation results. We present two questions: (1) Can existing IQA methods objectively evaluate recent IR algorithms? (2) With the focus on beating current benchmarks, are we getting better IR algorithms? To answer the questions and promote the development of IQA methods, we contribute a large-scale IQA dataset, called Perceptual Image Processing ALgorithms (PIPAL) dataset. Especially, this dataset includes the results of GAN-based IR algorithms, which are missing in previous datasets. We collect more than 1.13 million human judgements to assign subjective scores for PIPAL images using the more reliable "Elo system". Based on PIPAL, we present new benchmarks for both IQA and super-resolution methods. Our results indicate that existing IQA methods cannot fairly evaluate GAN-based IR algorithms. While using appropriate evaluation methods is important, IQA methods should also be updated along with the development of IR algorithms. At last, we shed light on how to improve the IQA performance on GAN-based distortion. Inspired by the find that the existing IQA methods have an unsatisfactory performance on the GAN-based distortion partially because of their low tolerance to spatial misalignment, we propose to improve the performance of an IQA network on GAN-based distortion by explicitly considering this misalignment. We propose the Space Warping Difference Network, which includes the novel l2 pooling layers and Space Warping Difference layers. Experiments demonstrate the effectiveness of the proposed method. © 2020, CC BY.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Deep Segment Attentive Embedding for Duration Robust Speaker Verification

Deep Segment Attentive Embedding for Duration Robust Speaker...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Bin Liu Shuai Nie Wenju Liu Hui Zhang Xiangang Li Changliang Li School of Artificial Intelligence University of Chinese Academy of Sciences China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China DiDi AI Labs China Kingsoft AI lab China

ISBN: (数字)9781728132488

ISBN: (纸本)9781728132495

Deep learning based speaker verification usually uses a fixed-length local segment randomly truncated from an utterance to learn the utterance-level speaker embedding, while using the average embedding of all segments of a test utterance to verify the speaker, which results in a critical mismatch between testing and training. This mismatch degrades the performance of speaker verification, especially when the durations of training and testing utterances are very different. To alleviate this issue, we propose the deep segment attentive embedding method to learn the unified speaker embeddings for utterances of variable duration. Each utterance is segmented by a sliding window and LSTM is used to extract the embedding of each segment. Instead of only using one local segment, we use the whole utterance to learn the utterance-level embedding by applying an attentive pooling to the embeddings of all segments. Moreover, the similarity loss of segment-level embeddings is introduced to guide the segment attention to focus on the segments with more speaker discriminations, and jointly optimized with the utterance-level embeddings loss. Systematic experiments on DiDi Speaker Dataset, Tongdun and VoxCeleb show that the proposed method significantly improves system robustness and achieves the relative EER reduction of 18.3%, 50% and 11.54%, respectively.

关键词： Training Speaker recognition Recurrent neural networks Learning (artificial intelligence) Feature extraction Testing

来源：评论

学校读者我要写书评

暂无评论

Geometry sharing network for 3D point cloud classification and segmentation

arXiv

引用

arXiv 2019年

作者： Xu, Mingye Zhou, Zhipeng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Siat Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

In spite of the recent progresses on classifying 3D point cloud with deep CNNs, large geometric transformations like rotation and translation remain challenging problem and harm the final classification performance. To address this challenge, we propose Geometry Sharing Network (GS-Net) which effectively learns point descriptors with holistic context to enhance the robustness to geometric transformations. Compared with previous 3D point CNNs which perform convolution on nearby points, GS-Net can aggregate point features in a more global way. Specially, GS-Net consists of Geometry Similarity Connection (GSC) modules which exploit Eigen-Graph to group distant points with similar and relevant geometric information, and aggregate features from nearest neighbors in both Euclidean space and Eigenvalue space. This design allows GS-Net to efficiently capture both local and holistic geometric features such as symmetry, curvature, convexity and connectivity. Theoretically, we show the nearest neighbors of each point in Eigenvalue space are invariant to rotation and translation. We conduct extensive experiments on public datasets, ModelNet40, ShapeNet Part. Experiments demonstrate that GS-Net achieves the state-of-the-art performances on major datasets, 93.3% on ModelNet40, and are more robust to geometric transformations. Code is released on https://***/MingyeXu/GS-Net. Copyright © 2019, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Graph Association for Person Re-Identification

Unsupervised Graph Association for Person Re-Identification

引用

International Conference on Computer Vision (ICCV)

作者： Jinlin Wu Hao Liu Yang Yang Zhen Lei Shengcai Liao Stan Li CBSR & NLPR Institute of Automation Beijing China. University of Chinese Academy of Sciences Beijing China. Inception Institute of Artificial Intelligence (IIAI) Abu Dhabi UAE National Lab. of Pattern Recognition. China

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

In this paper, we propose an unsupervised graph association (UGA) framework to learn the underlying view-invariant representations from the video pedestrian tracklets. The core points of UGA are mining the underlying cross-view associations and reducing the damage of noise associations. To this end, UGA is adopts a two-stage training strategy: (1) intra-camera learning stage and (2) intercamera learning stage. The former learns the intra-camera representation for each camera. While the latter builds a cross-view graph (CVG) to associate different cameras. By doing this, we can learn view-invariant representation for all person. Extensive experiments and ablation studies on seven re-id datasets demonstrate the superiority of the proposed UGA over most state-of-the-art unsupervised and domain adaptation re-id methods.

关键词： Cameras Training Noise measurement Scalability Graphics processing units Micromechanical devices Machine learning

来源：评论

学校读者我要写书评

暂无评论

DocRED: A large-scale document-level relation extraction dataset

arXiv

引用

arXiv 2019年

作者： Yao, Yuan Ye, Deming Li, Peng Han, Xu Lin, Yankai Liu, Zhenghao Liu, Zhiyuan Huang, Lixin Zhou, Jie Sun, Maosong Department of Computer Science and Technology Tsinghua University Beijing China Institute for Artificial Intelligence Tsinghua University Beijing China State Key Lab on Intelligent Technology and Systems Tsinghua University Beijing China Pattern Recognition Center WeChat AI Tencent Inc

Multiple entities in a document generally exhibit complex inter-sentence relations, and cannot be well handled by existing relation extraction (RE) methods that typically focus on extracting intra-sentence relations for single entity pairs. In order to accelerate the research on document-level RE, we introduce DocRED, a new dataset constructed from Wikipedia and Wikidata with three features: (1) DocRED annotates both named entities and relations, and is the largest human-annotated dataset for document-level RE from plain text;(2) DocRED requires reading multiple sentences in a document to extract entities and infer their relations by synthesizing all information of the document;(3) along with the human-annotated data, we also offer large-scale distantly supervised data, which enables DocRED to be adopted for both supervised and weakly supervised scenarios. In order to verify the challenges of document-level RE, we implement recent state-of-the-art methods for RE and conduct a thorough evaluation of these methods on DocRED. Empirical results show that DocRED is challenging for existing RE methods, which indicates that document-level RE remains an open problem and requires further efforts. Based on the detailed analysis on the experiments, we discuss multiple promising directions for future research. We make DocRED and the code for our baselines publicly available at https://***/thunlp/DocRED. Copyright © 2019, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Multi-paragraph reasoning with knowledge-enhanced graph neural network

arXiv

引用

arXiv 2019年

作者： Ye, Deming Lin, Yankai Liu, Zhenghao Liu, Zhiyuan Sun, Maosong Department of Computer Science and Technology Tsinghua University Beijing China Institute for Artificial Intelligence Tsinghua University Beijing China State Key Lab on Intelligent Technology and Systems Tsinghua University Beijing China Pattern Recognition Center WeChat AI Tencent Inc

Multi-paragraph reasoning is indispensable for open-domain question answering (OpenQA), which receives less attention in the current OpenQA systems. In this work, we propose a knowledge-enhanced graph neural network (KGNN), which performs reasoning over multiple paragraphs with entities. To explicitly capture the entities’ relatedness, KGNN utilizes relational facts in knowledge graph to build the entity graph. The experimental results show that KGNN outperforms in both distractor and full wiki settings than baselines methods on HotpotQA dataset. And our further analysis illustrates KGNN is effective and robust with more retrieved paragraphs. Copyright © 2019, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Expert Review of Algorithmic Mitotic Count Predictions Ensures High Reliability

引用

Journal of Comparative Pathology 2022年 191卷 12-12页

作者： C.A. Bertram R. Klopfleisch A. Bartel T.A. Donovan A. Fuchs-Baumgartinger K. Breininger M. Kiupel M. Aubreville Institute of Pathology University of Veterinary Medicine Vienna Austria Institute of Veterinary Pathology Institute for Veterinary Epidemiology and Biostatistics Freie Universität Berlin Berlin Germany Department of Anatomic Pathology Animal Medical Center New York USA Pattern Recognition Lab Computer Sciences Department Artificial Intelligence in Biomedical Engineering Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Veterinary Diagnostic Laboratory Michigan State University Lansing USA Technische Hochschule Ingolstadt Ingolstadt Germany

来源：评论

学校读者我要写书评

暂无评论

NumNet: Machine reading comprehension with numerical reasoning

arXiv

引用

arXiv 2019年

作者： Ran, Qiu Lin, Yankai Li, Peng Zhou, Jie Liu, Zhiyuan Pattern Recognition Center WeChat AI Tencent Inc China Department of Computer Science and Technology Tsinghua University Beijing China Institute for Artificial Intelligence Tsinghua University Beijing China State Key Lab on Intelligent Technology and Systems Tsinghua University Beijing China

Numerical reasoning, such as addition, subtraction, sorting and counting is a critical skill in human's reading comprehension, which has not been well considered in existing machine reading comprehension (MRC) systems. To address this issue, we propose a numerical MRC model named as NumNet, which utilizes a numerically-aware graph neural network to consider the comparing information and performs numerical reasoning over numbers in the question and passage. Our system achieves an EM-score of 64.56% on the DROP dataset, outperforming all existing machine reading comprehension models by considering the numerical relations among numbers. Copyright © 2019, The Authors. All rights reserved.

关键词： Graph neural networks

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

Author Correction: A comprehensive multi-domain dataset for mitotic figure detection

引用

Scientific data 2024年第1期11卷 717页

作者： Marc Aubreville Frauke Wilm Nikolas Stathonikos Katharina Breininger Taryn A Donovan Samir Jabari Mitko Veta Jonathan Ganz Jonas Ammeling Paul J van Diest Robert Klopfleisch Christof A Bertram Technische Hochschule Ingolstadt Ingolstadt Germany. marc.aubreville@thi.de. Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany. Department Artificial Intelligence in Biomedical Engineering Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany. Department of Pathology University Medical Center Utrecht Utrecht The Netherlands. Schwarzman Animal Medical Center New York USA. Department of Neuropathology Universitätsklinikum Erlangen Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany. Medical Image Analysis Group Eindhoven University of Technology Eindhoven the Netherlands. Technische Hochschule Ingolstadt Ingolstadt Germany. Institute of Veterinary Pathology Freie Universität Berlin Berlin Germany. Institute of Pathology University of Veterinary Medicine Vienna Vienna Austria.

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：