检索结果-内蒙古大学图书馆

Neural Pose Transfer by Spatially Adaptive Instance Normalization

学校读者我要写书评

暂无评论

Neural Pose Transfer by Spatially Adaptive Instance Normaliz...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jiashun Wang Chao Wen Yanwei Fu Haitao Lin Tianyun Zou Xiangyang Xue Yinda Zhang Fudan University School of Data Science and MOE Frontiers Center for Brain Science Shanghai Key Lab of Intelligent Information Processing Fudan University Academy of Engineering and Technology and Institute of AI and Robotics Fudan University Google LLC

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Pose transfer has been studied for decades, in which the pose of a source mesh is applied to a target mesh. Particularly in this paper, we are interested in transferring the pose of source human mesh to deform the target human mesh, while the source and target meshes may have different identity information. Traditional studies assume that the paired source and target meshes are existed with the point-wise correspondences of user annotated landmarks/mesh points, which requires heavy labelling efforts. On the other hand, the generalization ability of deep models is limited, when the source and target meshes have different identities. To break this limitation, we proposes the first neural pose transfer model that solves the pose transfer via the latest technique for image style transfer, leveraging the newly proposed component -- spatially adaptive instance normalization. Our model does not require any correspondences between the source and target meshes. Extensive experiments show that the proposed model can effectively transfer deformation from source to target meshes, and has good generalization ability to deal with unseen identities or poses of meshes. Code is available at https://***/jiashunwang/Neural-Pose-Transfer.

关键词： Shape Three-dimensional displays Feature extraction Strain Decoding Machine learning Task analysis

Modern deep learning in bioinformatics

学校读者我要写书评

暂无评论

Journal of Molecular Cell Biology 2020年第11期12卷 823-827页

作者： Haoyang Li Shuye Tian Yu Li Qiming Fang Renbo Tan Yijie Pan Chao Huang Ying Xu Xin Gao Cancer Systems Biology Center The China-Japan Union HospitalJilin UniversityChangchun 130033China MOE Key Laboratory of Symbolic Computation and Knowledge Engineering College of Computer Science and TechnologyJilin UniversityChangchun 130012China Department of Biology Southern University of Science and TechnologyShenzhen 518055China Computational Bioscience Research Center(CBRC) Computer Electrical and Mathematical Sciences and Engineering(CEMSE)DivisionKing Abdullah University of Science and Technology(KAUST)Thuwal 23955Saudi Arabia School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou 310018China Ningbo Institute of Information Technology Application Chinese Academy of SciencesNingbo 315040China Computational Systems Biology Lab Department of Biochemistry and Molecular Biology and Institute of BioinformaticsUniversity of GeorgiaAthensGA 30602USA

Deep learning(DL)has shown explosive growth in its application to bioinformatics and has demonstrated thrillingly promising power to mine the complex relationship hidden in large-scale biological and biomedical data.A number of comprehensive reviews have been published on such applications,ranging from high-level reviews with future perspectives to those mainly serving as tutorials.

关键词： has such she

XTQA: Span-Level Explanations for Textbook Question Answering

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ma, Jie Chai, Qi Liu, Jun Yin, Qingyu Wang, Pinghui Zheng, Qinghua Ministry of Education of Key Lab for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering The School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Amazon United States

Textbook Question Answering (TQA) is the task of correctly answering diagram or non-diagram questions given large multi-modal contexts consisting of abundant essays and diagrams. In real-world scenarios, an explainable TQA system plays a key role in deepening humans’ understanding of learned knowledge. However, there is no work to investigate how to provide explanations currently. To address this issue, we devise a novel architecture towards span-level eXplanations for TQA (XTQA). In this paper, spans are the combinations of sentences within a paragraph. The key idea is to consider the entire textual context of a lesson as candidate evidence, and then use our proposed coarse-to-fine grained Explanation Extracting (EE) algorithm to narrow down the evidence scope and extract the span-level explanations with varying lengths for answering different questions. The EE algorithm can also be integrated into other TQA methods to make them explainable and improve the TQA performance. Experimental results show that XTQA obtains the best overall explanation result (mIoU) of 52.38% on the first 300 questions of CK12-QA test splits, demonstrating the explainability of our method (non-diagram: 150 and diagram: 150). The results also show that XTQA achieves the best TQA performance of 36.46% and 36.95% on the aforementioned splits respectively. We have released our code in https://***/dr-majie/*** Codes 68T07 Copyright © 2020, The Authors. All rights reserved.

关键词： Textbooks

Dual encoding for video retrieval by text

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Dong, Jianfeng Li, Xirong Xu, Chaoxi Yang, Xun Yang, Gang Wang, Xun Wang, Meng College of Computer and Information Engineering Zhejiang Gongshang University Hangzhou310035 China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China The AI and Media Computing Lab School of Information Renmin University of China Beijing100872 China School of Computing National University of Singapore Singapore37580 Singapore School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

This paper attacks the challenging problem of video retrieval by text. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described exclusively in the form of a natural-language sentence, with no visual example provided. Given videos as sequences of frames and queries as sequences of words, an effective sequence-to-sequence cross-modal matching is crucial. To that end, the two modalities need to be first encoded into real-valued vectors and then projected into a common space. In this paper we achieve this by proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own. Our novelty is two-fold. First, different from prior art that resorts to a specific single-level encoder, the proposed network performs multi-level encoding that represents the rich content of both modalities in a coarse-to-fine fashion. Second, different from a conventional common space learning algorithm which is either concept based or latent space based, we introduce hybrid space learning which combines the high performance of the latent space and the good interpretability of the concept space. Dual encoding is conceptually simple, practically effective and end-to-end trained with hybrid space learning. Extensive experiments on four challenging video datasets show the viability of the new method. Code is available at https://***/danieljf24/hybrid_space. Copyright © 2020, The Authors. All rights reserved.

关键词： Signal encoding

Triplet Deep Subspace Clustering via Self-Supervised data Augmentation

学校读者我要写书评

暂无评论

Triplet Deep Subspace Clustering via Self-Supervised Data Au...

IEEE International Conference on data Mining (ICDM)

作者： Zhao Zhang Xianzhen Li Haijun Zhang Yi Yang Shuicheng Yan Meng Wang School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China School of Computer Science and Technology Soochow University Suzhou China Harbin Institute of Technology (Shenzhen) Shenzhen China Centre for Artificial Intelligence University of Technology Sydney Sydney NSW Australia Sea AI Lab (SAIL) & National University of Singapore Singapore

ISBN: (纸本)9781665423991

Deep subspace clustering (DSC) with the auto-encoder and self-expression layer is of great concern due to encouraging performance. However, existing methods usually adopt a “single-task” strategy based on a single dataset, without considering other related tasks or data. As such, they cannot discover other useful information to improve the clustering task. Besides, the local structure preservation of the latent codes in mapping is usually ignored. In this paper, we therefore present an effective “multi-task” strategy via the self-supervised data augmentation, and propose a new end-to-end trainable Triplet Deep Subspace Clustering Network (TDSC-net). Specifically, TDSC-net firstly generates triplet data (i.e., anchor, positive and negative data) from input data by a spectral clustering module and a self-supervised data augmentation module. This can enable it to inherit the merits of self-supervised learning and multitask learning implicitly. After that, TDSC-net builds a triplet deep autoencoder network with a self-expression layer, which takes the triplet data as input, where they share the common network layers (i.e., autoencoder and self-expression layers) over the triple tasks for complementary learning and mutual supervision. A triplet loss is also included to retain the local information of deep latent codes, which will also benefit the self-expression. Furthermore, TDSC-net separates the self-expression layer from decoding process to improve the efficiency of reconstruction. Extensive results on several public datasets demonstrate the effectiveness of our triplet-task DSC strategy.

关键词： Codes Conferences Multitasking Decoding data mining Task analysis

Personalizing search results using hierarchical RNN with query-aware attention

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Ge, Songwei Dou, Zhicheng Jiang, Zhengbao Nie, Jian-Yun Wen, Ji-Rong School of Information Renmin University of China DIRO Université de Montréal Beijing Key Laboratory of Big Data Management and Analysis Methods National Engineering Laboratory of Big Data System Software Beijing Institute of Technology Key Laboratory of Data Engineering and Knowledge Engineering MOE

Search results personalization has become an effective way to improve the quality of search engines. Previous studies extracted information such as past clicks, user topical interests, query click entropy and so on to tailor the original ranking. However, few studies have taken into account the sequential information underlying previous queries and sessions. Intuitively, the order of issued queries is important in inferring the real user interests. And more recent sessions should provide more reliable personal signals than older sessions. In addition, the previous search history and user behaviors should influence the personalization of the current query depending on their relatedness. To implement these intuitions, in this paper we employ a hierarchical recurrent neural network to exploit such sequential information and automatically generate user profile from historical data. We propose a query-aware attention model to generate a dynamic user profile based on the input query. Significant improvement is observed in the experiment with data from a commercial search engine when compared with several traditional personalization models. Our analysis reveals that the attention model is able to attribute higher weights to more related past sessions after fine training. Copyright © 2019, The Authors. All rights reserved.

关键词： Search engines

Using artificial intelligence to document the hidden RNA virosphere

学校读者我要写书评

暂无评论

四川生理科学杂志 2024年第10期46卷 2345-2345页

作者： Xin Hou National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases State Key Laboratory for Biocontrol School of Medicine Shenzhen Campus of Sun Yat-sen University Sun Yat-sen University Shenzhen China Apsara Lab Alibaba Cloud Intelligence Alibaba Group Hangzhou China Wuhan Centers for Disease Control and Prevention Wuhan China Polar Research Institute of China Shanghai China Department of Nursing The Fifth Affiliated Hospital Sun Yat-sen University Zhuhai China School of Geospatial Engineering and Science Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai) Sun Yat-sen University Zhuhai China Key Laboratory of Comprehensive Observation of Polar Environment Ministry of Education Sun Yat-sen University Zhuhai China Ministry of Education Key Laboratory of Biodiversity Science and Ecological Engineering National Observations and Research Station for Wetland Ecosystems of the Yangtze Estuary Institute of Biodiversity Science and Institute of Eco-Chongming School of Life Sciences Fudan University Shanghai Shanghai China Centre for Virus Research Westmead Institute for Medical Research Westmead NSW Australia School of Medical Sciences The University of Sydney Sydney NSW 2006 Australia College of Life Sciences Zhejiang University Hangzhou China School of Life Science Guangzhou University Guangzhou China Key Laboratory of Pathogen Infection Prevention and Control (MOE) State Key Laboratory of Respiratory Health and Multimorbidity National Institute of Pathogen Biology Chinese Academy of Medical Sciences & Peking Union Medical College Beijing China School of Public Health (Shenzhen) Shenzhen Campus of Sun Yat-sen University Sun Yat-sen University Shenzhen China Guangzhou National Laboratory Guangzhou International Bio-Island Guangzhou China Department of Infectious Diseases and Public Health Jockey Club College of Veterinary Medicine and Life Sciences City University of Hong Kong Hong Kong SAR China Laboratory of Data Disco

Current metagenomic tools can fail to identify highly divergent RNA *** developed a deep learning algorithm,termed LucaProt,to discover highly divergent RNA-dependent RNA polymerase(RdRP)sequences in 10,487 metatranscriptomes generated from diverse global *** integrates both sequence and predicted structural information,enabling the accurate detection of RdRP *** this approach,we identified 161,979 potential RNA virus species and 180 RNA virus supergroups,including many previously poorly studied groups,as well as RNA virus genomes of exceptional length(up to 47,250 nucleotides)and genomic complexity.

关键词： artificial exceptional integrate

Instance credibility inference for few-shot learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Yikai Xu, Chengming Liu, Chen Zhang, Li Fu, Yanwei School of Data Science Fudan University China Department of Engineering Science University of Oxford United Kingdom MOE Frontiers Center for Brain Science Fudan University China Shanghai Key Lab of Intelligent Information Processing Fudan University China

Few-shot learning (FSL) aims to recognize new objects with extremely limited training data for each category. Previous efforts are made by either leveraging meta-learning paradigm or novel principles in data augmentation to alleviate this extremely data-scarce problem. In contrast, this paper presents a simple statistical approach, dubbed Instance Credibility Inference (ICI) to exploit the distribution support of unlabeled instances for few-shot learning. Specifically, we first train a linear classifier with the labeled few-shot examples and use it to infer the pseudo-labels for the unlabeled data. To measure the credibility of each pseudo-labeled instance, we then propose to solve another linear regression hypothesis by increasing the sparsity of the incidental parameters and rank the pseudo-labeled instances with their sparsity degree. We select the most trustworthy pseudo-labeled instances alongside the labeled examples to re-train the linear classifier. This process is iterated until all the unlabeled samples are included in the expanded training set, i.e. the pseudo-label is converged for unlabeled data pool. Extensive experiments under two few-shot settings show that our simple approach can establish new state-of-the-arts on four widely used few-shot learning benchmark datasets including miniImageNet, tieredImageNet, CIFAR-FS, and CUB. Our code is available at: https://***/Yikai-Wang/ICI-FSL Copyright © 2020, The Authors. All rights reserved.

关键词： Machine learning

GraphNorm: A principled approach to accelerating graph neural network training

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Cai, Tianle Luo, Shengjie Xu, keyulu He, Di Liu, Tie-Yan Wang, Liwei Department of Electrical and Computer Engineering Princeton University Zhongguancun Haihua Institute for Frontier Information Technology Key Laboratory of Machine Perception MOE School of EECS Peking University Center for Data Science Peking University Pazhou Lab Microsoft Research

Normalization is known to help the optimization of deep neural networks. Curiously, different architectures require specialized normalization methods. In this paper, we study what normalization is effective for Graph Neural Networks (GNNs). First, we adapt and evaluate the existing methods from other domains to GNNs. Faster convergence is achieved with InstanceNorm compared to BatchNorm and LayerNorm. We provide an explanation by showing that InstanceNorm serves as a preconditioner for GNNs, but such preconditioning effect is weaker with BatchNorm due to the heavy batch noise in graph datasets. Second, we show that the shift operation in InstanceNorm results in an expressiveness degradation of GNNs for highly regular graphs. We address this issue by proposing GraphNorm with a learnable shift. Empirically, GNNs with GraphNorm converge faster compared to GNNs using other normalization. GraphNorm also improves the generalization of GNNs, achieving better performance on graph classification benchmarks. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph neural networks