检索结果-内蒙古大学图书馆

Object detection with deep learning: A review

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zhao, Zhong-Qiu Zheng, Peng Xu, Shou-Tao Wu, Xindong College of Computer Science and Information Engineering Hefei University of Technology China School of Computing and Informatics University of Louisiana Lafayette United States

Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable architectures. Their performance easily stagnates by constructing complex ensembles which combine multiple low-level image features with high-level context from object detectors and scene classifiers. With the rapid development in deep learning, more powerful tools, which are able to learn semantic, high-level, deeper features, are introduced to address the problems existing in traditional architectures. These models behave differently in network architecture, training strategy and optimization function, etc. In this paper, we provide a review on deep learning based object detection frameworks. Our review begins with a brief introduction on the history of deep learning and its representative tool, namely Convolutional Neural Network (CNN). Then we focus on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further. As distinct specific detection tasks exhibit different characteristics, we also briefly survey several specific tasks, including salient object detection, face detection and pedestrian detection. Experimental analyses are also provided to compare various methods and draw some meaningful conclusions. Finally, several promising directions and tasks are provided to serve as guidelines for future work in both object detection and relevant neural network based learning systems. Copyright © 2018, The Authors. All rights reserved.

关键词： Object detection

How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bunne, Charlotte Roohani, Yusuf Rosen, Yanay Gupta, Ankit Zhang, Xikun Roed, Marcel Alexandrov, Theo AlQuraishi, Mohammed Brennan, Patricia Burkhardt, Daniel B. Califano, Andrea Cool, Jonah Dernburg, Abby F. Ewing, Kirsty Fox, Emily B. Haury, Matthias Herr, Amy E. Horvitz, Eric Hsu, Patrick D. Jain, Viren Johnson, Gregory R. Kalil, Thomas Kelley, David R. Kelley, Shana O. Kreshuk, Anna Mitchison, Tim Otte, Stephani Shendure, Jay Sofroniew, Nicholas J. Theis, Fabian Theodoris, Christina V. Upadhyayula, Srigokul Valer, Marc Wang, Bo Xing, Eric Yeung-Levy, Serena Zitnik, Marinka Karaletsos, Theofanis Regev, Aviv Lundberg, Emma Leskovec, Jure Quake, Stephen R. Department of Computer Science Stanford University StanfordCA United States Genentech South San FranciscoCA United States Chan Zuckerberg Initiative Redwood CityCA United States School of Computer and Communication Sciences School of Life Sciences EPFL Lausanne Switzerland Arc Institute Palo AltoCA United States KTH Royal Institute of Technology Science for Life Laboratory Department of Protein Science Stockholm Sweden Department of Bioengineering Stanford University StanfordCA United States Department of Pharmacology University of California San DiegoCA United States Department of Bioengineering University of California San DiegoCA United States Department of Systems Biology Columbia University New YorkNY United States Cellarity SomervilleMA United States Vagelos College of Physicians and Surgeons Columbia University Irving Medical Center New YorkNY United States Chan Zuckerberg Biohub New YorkNY United States Department of Molecular and Cell Biology University of California Berkeley BerkeleyCA United States Department of Statistics Stanford University StanfordCA United States Chan Zuckerberg Biohub San Francisco CA United States Chan Zuckerberg Institute for Advanced Biological Imaging Redwood CityCA United States Department of Bioengineering University of California BerkeleyCA United States Microsoft Research RedmondWA United States Center for Computational Biology University of California Berkeley BerkeleyCA United States Google Research Mountain ViewCA United States NewLimit San FranciscoCA United States Schmidt city United States Calico Life Sciences LLC San FranciscoCA United States Chan Zuckerberg Biohub Chicago IL United States Northwestern University EvanstonIL United States Cell Biology and Biophysics Unit European Molecular Biology Laboratory Heidelberg Germany Department of Systems Biology Harvard Medical School BostonMA United States Department of Genome Sciences University of Washington SeattleWA Unit

The cell is arguably the most fundamental unit of life and is central to understanding biology. Accurate modeling of cells is important for this understanding as well as for determining the root causes of disease. Recent advances in artificial intelligence (AI), combined with the ability to generate large-scale experimental data, present novel opportunities to model cells. Here we propose a vision of leveraging advances in AI to construct virtual cells, high-fidelity simulations of cells and cellular systems under different conditions that are directly learned from biological data across measurements and scales. We discuss desired capabilities of such AI Virtual Cells, including generating universal representations of biological entities across scales, and facilitating interpretable in silico experiments to predict and understand their behavior using Virtual Instruments. We further address the challenges, opportunities and requirements to realize this vision including data needs, evaluation strategies, and community standards and engagement to ensure biological accuracy and broad utility. We envision a future where AI Virtual Cells help identify new drug targets, predict cellular responses to perturbations, as well as scale hypothesis exploration. With open science collaborations across the biomedical ecosystem that includes academia, philanthropy, and the biopharma and AI industries, a comprehensive predictive understanding of cell mechanisms and interactions has come into reach. © 2024, CC BY.

关键词： Virtual environments

Document-specific keyphrase candidate search and ranking

学校读者我要写书评

暂无评论

Expert Systems with Applications 2018年 97卷 163-176页

作者： Wang, Qingren Sheng, Victor S. Wu, Xindong Hefei University of Technology 193 Tunxi Road Hefei 230009 Anhui Province China University of Central Arkansas 201 Donaghey Ave. Conway 72035 AR United States School of Computing and Informatics University of Louisiana at Lafayette 222 James R. Oliver Hall Lafayette 70504-3694 LA United States

This paper proposes an approach KeyRank to extract proper keyphrases from a document in English. It first searches all keyphrase candidates from the document, and then ranks them for selecting top-N ones as final keyphrases. Existing studies show that extracting a complete keyphrase candidate set that includes semantic relations in context, and evaluating the effectiveness of each candidate are crucial to extract high quality keyphrases from documents. Based on that words do not repeatedly appear in an effective keyphrase in English, a novel keyphrase candidate search algorithm using sequential pattern mining with gap constraints (called KCSP) is proposed to extract keyphrase candidates for KeyRank. And then an effectiveness evaluation measure pattern frequency with entropy (called PF-H) is proposed for KeyRank to rank these keyphrase candidates. Our experimental results show that KeyRank has better performance. Its first component KCSP is much more efficient than a closely related approach SPMW, and its second component PF-H is an effective evaluation mechanism for ranking keyphrase candidates.¹ © 2017 Elsevier Ltd

关键词： Entropy Keyphrase candidate ranking Keyphrase candidate search Sequential pattern mining

Maintaining reading experience continuity across e-book revisions

学校读者我要写书评

暂无评论

Research and Practice in technology Enhanced Learning 2018年第1期13卷 1-16页

作者： Yang, Christopher Flanagan, Brendan Akcapinar, Gokhan Ogata, Hiroaki Graduate School of Informatics Kyoto University 36-1 Yoshida-Honmachi Sakyo-ku Kyoto 606-8501 Japan Academic Center for Computing and Media Studies Kyoto University Yoshida-Nihonmatsu Sakyo-ku Kyoto 606-8501 Japan Department of Computer Education and Instructional Technology Hacettepe University Ankara 06800 Turkey

E-book reader supports users to create digital learning footprints in many forms like highlighting sentences or taking memos. Nowadays, it also allows an instructor to update their e-books in the e-book reader. However, e-book users often face problems when trying to find learning footprints they made in a new version e-book. Thus, users’ reading experience continuity across e-book revisions is hard to be maintained and seems to become a shortcoming within the e-book system. In this paper, in order to maintain users’ reading experience continuity, we deal with the transfer of learning footprints such as a marker, memo, and bookmark across e-book revisions on an e-book reader in a coursework scenario. We first give introduction and related works to demonstrate how researchers dedicated on the problem mentioned in this paper and page similarity comparison. Then, we compare three page similarity comparison methods using similarity computing models to compute page pairwise similarity in image level, text level, and image & text level. In the analysis, for each level, we analyze the performance of transferring learning footprint across e-book revisions and also the optimal threshold for similar page determination. After that, we give the analysis results to show the performances of three methods in image level, text level, and image & text level, and then, the error analysis is presented to specify the error types that occur in the results. We then propose page image & text similarity comparison as the optimal method to automatically transfer learning footprints across e-book revisions based on the analysis results and error analysis among three compared methods. Finally, the discussion and conclusions are shown in the end of this paper. © 2018, The Author(s).

关键词： E-book reader Image similarity processing Learning footprint Page similarity comparison Text similarity processing

Linear response theory in coupled phase oscillators with general coupling functions

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Terada, Yu Yamaguchi, Yoshiyuki Y. Laboratory for Neural Computation and Adaptation RIKEN Center for Brain Science 2-1 Hirosawa WakoSaitama351-0198 Japan Department of Mathematical and Computing Science Tokyo Institute of Technology Tokyo152-8552 Japan Department of Applied Mathematics and Physics Graduate School of Informatics Kyoto University Kyoto606-8501 Japan

We develop a linear response theory through computing the asymptotic value of the order parameter from the linearized equation of continuity around the nonsynchronized reference state with the aid of the Laplace transform in time. The proposed theory is applicable to a wide class of coupled phase oscillator systems, and allows any coupling functions, any natural frequency distributions, any phase-lag parameters, and any values of a time-delay parameter. This generality is in contrast to the limitation of the previous methods of the Ott–Antonsen ansatz and the self-consistent equation for an order parameter, which are restricted to a model family whose coupling function consists of only a single sinusoidal function. The theory is verified by numerical simulations. Copyright © 2019, The Authors. All rights reserved.

关键词： Laplace transforms

Deep localization of subcellular protein structures from fluorescence microscopy images

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Tahir, Muhammad Anwar, Saeed Mian, Ajmal Muzaffar, Abdul Wahab College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia Data61 The Commonwealth Scientific and Industrial Research Organisation Australia Department of Computer Science and Engineering The Australian National University Australia School of Computer Science University of Technology Sydney Australia Computer Science and Software Engineering The University of Western Australia

Accurate localization of proteins from fluorescence microscopy images is challenging due to the inter-class similarities and intra-class disparities introducing grave concerns in addressing multi-class classification problems. Conventional machine learning-based image prediction pipelines rely heavily on pre-processing such as normalization and segmentation followed by hand-crafted feature extraction to identify useful, informative, and application-specific features. Here, we demonstrate that deep learning-based pipelines can effectively classify protein images from different datasets. We propose an end-to-end Protein Localization Convolutional Neural Network (PLCNN) that classifies protein images more accurately and reliably. PLCNN processes raw imagery without involving any pre-processing steps and produces outputs without any customization or parameter adjustment for a particular dataset. Experimental analysis is performed on five benchmark datasets. PLCNN consistently outperformed the existing state-of-the-art approaches from traditional machine learning and deep architectures. This study highlights the importance of deep learning for the analysis of fluorescence microscopy protein imagery. The proposed deep pipeline can better guide drug designing procedures in the pharmaceutical industry and open new avenues for researchers in computational biology and bioinformatics. © 2019, CC BY.

关键词： Fluorescence microscopy

Learning bidirectional LSTM networks for synthesizing 3D mesh animation sequences

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Qiao, Yi-Ling Gao, Lin Lai, Yu-Kun Xia, Shihong Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences School of Computer and Control Engineering University of Chinese Academy of Sciences School of Computer Science & Informatics Cardiff University

In this paper, we present a novel method for learning to synthesize 3D mesh animation sequences with long short-term memory (LSTM) blocks and mesh-based convolutional neural networks (CNNs). Synthesizing realistic 3D mesh animation sequences is a challenging and important task in computer animation. To achieve this, researchers have long been focusing on shape analysis to develop new interpolation and extrapolation techniques. However, such techniques have limited learning capabilities and therefore can produce unrealistic animation. Deep architectures that operate directly on mesh sequences remain unexplored, due to the following major barriers: meshes with irregular triangles, sequences containing rich temporal information and flexible deformations. To address these, we utilize convolutional neural networks defined on triangular meshes along with a shape deformation representation to extract useful features, followed by LSTM cells that iteratively process the features. To allow completion of a missing mesh sequence from given endpoints, we propose a new weight-shared bidirectional structure. The bidirectional generation loss also helps mitigate error accumulation over iterations. Benefiting from all these technical advances, our approach outperforms existing methods in sequence prediction and completion both qualitatively and quantitatively. Moreover, this network can also generate follow-up frames conditioned on initial shapes and improve the accuracy as more bootstrap models are provided, which other works in the geometry processing domain cannot achieve. Copyright © 2018, The Authors. All rights reserved.

关键词： Mesh generation

Global fire season severity analysis and forecasting

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Ferreira, Leonardo N. Vega-Oliveros, Didier A. Zhao, Liang Cardoso, Manoel F. Macau, Elbert E.N. Associated Laboratory for Computing and Applied Mathematics National Institute for Space Research São José Dos Campos - SP Brazil School of Informatics Computing and Engineering Indiana University BloomingtonIN United States Department of Computing and Mathematics University of São Paulo Ribeirão Preto - SP Brazil Center for Earth System Science National Institute for Space Research Cachoeira Paulista - SP Brazil Institute of Science and Technology Federal University of São Paulo São José Dos Campos - SP Brazil

Fire activity has a huge impact on human lives. Different models have been proposed to predict fire activity, which can be classified into global and regional ones. Global fire models focus on longer timescale simulations and can be very complex. Regional fire models concentrate on seasonal forecasting but usually require inputs that are not available in many places. Motivated by the possibility of having a simple, fast, and general model, we propose a seasonal fire prediction methodology based on time series forecasting methods. It consists of dividing the studied area into grid cells and extracting time series of fire counts to fit the forecasting models. We apply these models to estimate the fire season severity (FSS) from each cell, here defined as the sum of the fire counts detected in a season. Experimental results using a global fire detection data set show that the proposed approach can predict FSS with a relatively low error in many regions. The proposed approach is reasonably fast and can be applied on a global scale. Copyright © 2019, The Authors. All rights reserved.

关键词： Climate change

Quantum Games and Interactive Tools for Quantum Technologies Outreach and Education

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Seskir, Zeki C. Migdal, Piotr Weidner, Carrie Anupam, Aditya Case, Nicky Davis, Noah Decaroli, Chiara Ercan, İlke Foti, Caterina Gora, Pawel Jankiewicz, Klementyna La Cour, Brian R. Malo, Jorge Yago Maniscalco, Sabrina Naeemi, Azad Nita, Laurentiu Parvin, Nassim Scafirimuto, Fabio Sherson, Jacob F. Surer, Elif Wootton, James Yeh, Lia Zabello, Olga Chiofalo, Marilù Karlsruhe Institute of Technology ITAS Karlstraße 11 Karlsruhe76133 Germany Quantum Flytrap ul. Ceglowska 29 Warsaw01-809 Poland Quantum Engineering Technology Laboratories H.H. Wills Physics Laboratory Department of Electrical and Electronic Engineering University of Bristol BristolBS8 1FD United Kingdom Georgia Institute of Technology School of Literature Media and Communication 686 Cherry St NW AtlantaGA30313 United States The University of Texas at Austin Center for Quantum Research Applied Research Laboratories 10000 Burnet Rd AustinTX78758 United States National Quantum Computing Center Oxfordshire DidcotOX11 0GD United Kingdom TU Delft Department of Microelectronics Mekelweg 4 Delft2628 CD Netherlands QPlayLearn Aalto University InstituteQ - The Finnish Quantum Institute Department of Applied Physics AaltoFI-00076 11000 Finland Quantum AI Foundation Sanocka 9/103 Warsaw02-110 Poland University of Pisa Department of Physics Largo Bruno Pontecorvo 3 PisaI-56126 Italy University of Helsinki InstituteQ - The Finnish Quantum Institute Department of Physics Helsinki Finland Georgia Institute of Technology School of Electrical and Computer Engineering 777 Atlantic Drive NW AtlantaGA30332 United States Quarks Interactive Strada Bailor 93a Miercurea-Ciuc Harghita4500 Romania IBM Quantum IBM Research - Zurich Säumerstrasse 4 Rüschlikon8803 Switzerland ScienceAtHome Fuglesangs Allé 4 Aarhus8210 Denmark Aarhus University Institute for Physics and Astronomy Ny Munkegade 120 Aarhus8000 Denmark Middle East Technical University Graduate School of Informatics Department of Modeling and Simulation Üniversiteler Mah. Dumlupınar Blv. No:1 Ankara06800 Turkey University of Oxford Department of Computer Science Wolfson Building Parks Road OxfordOX1 3QD United Kingdom IBM Quantum IBM T. J. Watson Research Center Yorktown HeightsNY10598 United States Offenburg University of Applied Sciences Department of Business and Industrial Eng

In this article, we provide an extensive overview of a wide range of quantum games and interactive tools that have been employed by the community in recent years. The paper presents selected tools, as described by their developers. The list includes Hello Quantum, Hello Qiskit, Particle in a Box, Psi and Delta, QPlayLearn, Virtual Lab by Quantum Flytrap, Quantum Odyssey, ScienceAtHome, and The Virtual Quantum Optics Laboratory. Additionally, we present events for quantum game development: hackathons, game jams, and semester projects. Furthermore, we discuss the Quantum Technologies Education for Everyone (QUTE4E) pilot project, which illustrates an effective integration of these interactive tools with quantum outreach and education activities. Finally, we aim at providing guidelines for incorporating quantum games and interactive tools in pedagogic materials to make quantum technologies more accessible for a wider population. Copyright © 2022, The Authors. All rights reserved.

关键词： Quantum optics