B体育·(sports)官方网站

访问arxivdaily.com，获取带摘要的学术速递，更多学科、收藏、评论、搜索……应有尽有。同步公众号(arXiv每日学术速递)，欢迎关注

【1】 Soccer Event Detection Using Deep Learning
标题：基于深度学习的足球事件检测
作者：Ali Karimi,Ramin Toosi,Mohammad Ali Akhaee
机构*：University of Tehran, Tehran, Iran.
链接：https://arxiv.org/abs/2102.04331

【2】 Plotting time: On the usage of CNNs for time series classification
标题：绘图时间：CNN在时间序列分类中的应用
作者：Nuno M. Rodrigues,João E. Batista,Leonardo Trujillo,Bernardo Duarte,Mario Giacobini,Leonardo Vanneschi,Sara Silva
机构*：LASIGE, Faculdade de Ciencias da Universidade de Lisboa, Campo Grande,-, Lisboa, Portugal, Departamento de Ingenieria Electrica y Electronica, Tecnologico Nacional, MexicoIT de Tijuana, BMARE-Marine and Environmental Sciences Centre, Faculdade de Ciencias da Universidade de Lisboa, Departamento de Biologia Vegetal, Faculdade de Ciencias da Universidade de Lisboa, Campo Grande, Data Analysis and Modeling Unit, University of Torino, Italy, NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de, Campolide,-, Lisboa, Portugal
链接：https://arxiv.org/abs/2102.04179

【3】 Improving filling level classification with adversarial training
标题：用对抗性训练提高填充度分级
作者：Apostolos Modas,Alessio Xompero,Ricardo Sanchez-Matilla,Pascal Frossard,Andrea Cavallaro
机构*：LTS, Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland, Centre for Intelligent Sensing, Queen Mary University of London, UK
链接：https://arxiv.org/abs/2102.04057

【4】 Towards Accurate RGB-D Saliency Detection with Complementary Attention and Adaptive Integration
标题：基于互补注意和自适应积分的精确RGB-D显著性检测
作者：Hong-Bo Bi,Zi-Qi Liu,Kang Wang,Bo Dong,Geng Chen,Ji-Quan Ma
机构*：Northeast Petroleum University, Daqing , China., University of Shanghai for Science and Technology, Shanghai , China, CInception Institute of Artificial Intelligence, Abu Dhabi, UAE, Heilongjiang University, Harbin , China, ARTICLE INFO
链接：https://arxiv.org/abs/2102.04046

【5】 Damage detection using in-domain and cross-domain transfer learning
标题：基于域内和跨域转移学习的损伤检测
作者：Zaharah A. Bukhsh,Nils Jansen,Aaqib Saeed
机构*：Eindhoven University of Technology, Radboud University, Eindhoven, The Netherlands, Nijmegen, The Netherlands
备注：15 pages, 4 figures, 5 tables
链接：https://arxiv.org/abs/2102.03858

【6】 DPointNet: A Density-Oriented PointNet for 3D Object Detection in Point Clouds
标题：DPointNet：一种面向密度的点云三维目标检测点网
作者：Jie Li,Yu Hu
机构*：Research Center for Intelligent Computing Systems, Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences
链接：https://arxiv.org/abs/2102.03747

【7】 Unsupervised Audio-Visual Subspace Alignment for High-Stakes Deception Detection
标题：基于无监督视听子空间对齐的高风险欺骗检测
作者：Leena Mathur,Maja J Matarić
机构*：University of Southern California, Los Angeles, CA
备注：Accepted at ICASSP 2021 \c{opyright} 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of copyrighted components of this work
链接：https://arxiv.org/abs/2102.03673

【8】 Gated3D: Monocular 3D Object Detection From Temporal Illumination Cues
标题：Gated3D：基于时间光照线索的单目三维目标检测
作者：Frank Julca-Aguilar,Jason Taylor,Mario Bijelic,Fahim Mannan,Ethan Tseng,Felix Heide
机构*：Algolux ,Daimler AG ,Ulm University ,Princeton University
链接：https://arxiv.org/abs/2102.03602

【9】 SM+: Refined Scale Match for Tiny Person Detection
标题：SM+：用于微小人物检测的精细尺度匹配
作者：Nan Jiang,Xuehui Yu,Xiaoke Peng,Yuqi Gong,Zhenjun Han
机构*：University of Chinese Academy of Sciences, Beijing, China
备注：5 pages, 2 figures
链接：https://arxiv.org/abs/2102.03558

【10】 Video-based Hierarchical Species Classification for Longline Fishing Monitoring
标题：基于视频的延绳钓监测层次化物种分类
作者：Jie Mei,Jenq-Neng Hwang,Suzanne Romain,Craig Rose,Braden Moore,Kelsey Magrane
机构*：University of Washington, Seattle, WA , USA
备注：To be published in CVAUI2020 in conjunction with ICPR2020
链接：https://arxiv.org/abs/2102.03520

【11】 Custom Object Detection via Multi-Camera Self-Supervised Learning
标题：基于多摄像机自监督学习的自定义目标检测
作者：Yan Lu,Yuanchao Shu
机构*：INew York University, Microsoft Research
备注：7 pages, 12 figures
链接：https://arxiv.org/abs/2102.03442

【12】 Rapid Classification of Glaucomatous Fundus Images
标题：青光眼眼底图像的快速分类
作者：Hardit Singh,Simarjeet Saini,Vasudevan Lakshminarayanan
备注：Submitted for publication in JOSA A: Optics and Image Science, currently under revision
链接：https://arxiv.org/abs/2102.04400

【13】 Learned Camera Gain and Exposure Control for Improved Visual Feature Detection and Matching
标题：用于改进视觉特征检测和匹配的学习相机增益和曝光控制
作者：Justin Tomasi,Brandon Wagstaff,Steven L. Waslander,Jonathan Kelly
备注：Accepted to IEEE Robotics and Automation Letters and submitted to the IEEE International Conference on Robotics and Automation (ICRA) 2021
链接：https://arxiv.org/abs/2102.04341

【14】 Deep Learning Models May Spuriously Classify Covid-19 from X-ray Images Based on Confounders
标题：基于混杂因子的深度学习模型可能对X射线图像中的冠状病毒进行虚假分类
作者：Kaoutar Ben Ahmed,Lawrence O. Hall,Dmitry B. Goldgof,Gregory M. Goldgof,Rahul Paul
机构*：University of South Florida, Tampa, USA, University of California, San Francisco, USA., These authors contributed equally., These authors jointly supervised.
链接：https://arxiv.org/abs/2102.04300

【15】 Efficient Certified Defenses Against Patch Attacks on Image Classifiers
标题：基于图像分类器的高效抗补丁攻击认证防御
作者：Jan Hendrik Metzen,Maksym Yatsura
机构*：Bosch Center for Artificial Intelligence, Robert Bosch GmbH, Robert-Bosch-Campus , Renningen, Germany
备注：accepted at ICLR 2021
链接：https://arxiv.org/abs/2102.04154

【16】 Automatic Breast Lesion Detection in Ultrafast DCE-MRI Using Deep Learning
标题：基于深度学习的超高速DCE-MRI乳腺病变自动检测
作者：Fazael Ayatollahi,Shahriar B. Shokouhi,Ritse M. Mann,Jonas Teuwen
机构*：Iran University of Science and Technology (IUST), Tehran, Iran, Radboud University Medical Center, Nijmegen the Netherlands, Iran University of Science and Technology(IUST), Tehran, Iran, Radboud University Medical Center Nijmegen, the Netherlands, Netherlands Cancer Institute, Amsterdam, the Netherlands, Corresponding Author:
链接：https://arxiv.org/abs/2102.03932

【17】 Sparsely ensembled convolutional neural network classifiers via reinforcement learning
标题：基于强化学习的稀疏集成卷积神经网络分类器
作者：Roman Malashin
链接：https://arxiv.org/abs/2102.03921

【18】 MIN2Net: End-to-End Multi-Task Learning for Subject-Independent Motor Imagery EEG Classification
标题：MIN2Net：端到端多任务学习的独立于主体的运动想象脑电信号分类
作者：Phairot Autthasan,Rattanaphon Chaisaen,Thapanun Sudhawiyangkul,Phurin Rangpong,Suktipol Kiatthaveephong,Nat Dilokthanakul,Gun Bhakdisongkhram,Huy Phan,Cuntai Guan,Theerawit Wilaiprasitporn
链接：https://arxiv.org/abs/2102.03814

【19】 Privacy-Preserving Video Classification with Convolutional Neural Networks
标题：基于卷积神经网络的隐私保护视频分类
作者：Sikha Pentyala,Rafael Dowsley,Martine De Cock
链接：https://arxiv.org/abs/2102.03513

【1】 TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
标题：TransUNet：Transformer为医学图像分割提供强大的编码器
作者：Jieneng Chen,Yongyi Lu,Qihang Yu,Xiangde Luo,Ehsan Adeli,Yan Wang,Le Lu,Alan L. Yuille,Yuyin Zhou
机构*： Johns Hopkins University, University of Electronic Science and Technology of China, Stanford Universit, East China Normal University, SPAII Inc.
备注：13 pages, 3 figures
链接：https://arxiv.org/abs/2102.04306

【2】 Template-Free Try-on Image Synthesis via Semantic-guided Optimization
标题：基于语义引导优化的无模板试穿图像合成
作者：Chien-Lung Chou,Chieh-Yun Chen,Chia-Wei Hsieh,Hong-Han Shuai,Jiaying Liu,Wen-Huang Cheng
备注：Accepted by IEEE TNNLS (2021). 14 pages including 2 pages of reference
链接：https://arxiv.org/abs/2102.03503

【3】 MudrockNet: Semantic Segmentation of Mudrock SEM Images through Deep Learning
标题：MudrockNet：基于深度学习的Mudrock SEM图像语义分割
作者：Abhishek Bihani,Hugh Daigle,Javier E. Santos,Christopher Landry,Masa Prodanovic,Kitty Milliken
机构*：Milliken, The University of Texas at, Austin, Austin, Texas, USA; ,Center for Subsurface Energy and the Environment, University of, Texas at Austin, Austin, Texas, USA; ,Bureau of Economic Geology, University of Texas at
备注：24 pages, 8 figures, submitted to Computers and Geosciences
链接：https://arxiv.org/abs/2102.03393

【4】 A Systematic Approach for MRI Brain Tumor Localization, and Segmentation using Deep Learning and Active Contouring
标题：一种基于深度学习和主动轮廓的MRI脑肿瘤定位与分割系统方法
作者：Shanaka Ramesh Gunasekara,H. N. Tb体育下载app. K. Kaldera,Maheshi B. Dissanayake
机构*：University, ofPeradeniya, Sri Lanka
备注：accepted for publication in Journal of Healthcare Engineering, Hindawi in 2021
链接：https://arxiv.org/abs/2102.03532

【1】 Reliable Probabilistic Face Embeddings in the Wild
标题：野外可靠的概率人脸嵌入
作者：Kai Chen,Qi Lv,Taihe Yi,Zhengming Yi
机构*：College of Computer, National University of Defense Technology, Changsha, China, College of Meteorology and Oceanography, National University of Defense Technology, Changsha, China
备注：14 pages
链接：https://arxiv.org/abs/2102.04075

【2】 One-shot Face Reenactment Using Appearance Adaptive Normalization
标题：基于外观自适应归一化的一次人脸重现
作者：Guangming Yao,Yi Yuan,Tianjia Shao,Shuang Li,Shanqi Liu,Yong Liu,Mengmeng Wang,Kun Zhou
机构*： NetEase Fuxi Al Lab, State Key Lab of CAD&CG, Zhejiang University, Beijing Institute of Technology, Institute of Cyber-Systems and Control, Zhejiang University
备注：9 pages, 8 figures,3 tables ,Accepted by AAAI2021
链接：https://arxiv.org/abs/2102.03984

【3】 BinaryCoP: Binary Neural Network-based COVID-19 Face-Mask Wear and Positioning Predictor on Edge Devices
标题：BinaryCoP：基于二值神经网络的边缘设备冠状病毒口罩磨损与定位预测器
作者：Nael Fasfous,Manoj-Rohit Vemparala,Alexander Frickenstein,Lukas Frickenstein,Walter Stechele
机构*：Technical University of Munich(.http://ctum.de)
链接：https://arxiv.org/abs/2102.03456

【1】 Solid Texture Synthesis using Generative Adversarial Networks
标题：基于产生式对抗网络的立体纹理合成
作者：Xin Zhao,Lin Wang,Jifeng Guo,Bo Yang,Junteng Zheng,Fanqi Li
链接：https://arxiv.org/abs/2102.03973

【2】 Adversarial Training of Variational Auto-encoders for Continual Zero-shot Learning
标题：连续Zero-Shot学习变分自动编码器的对抗性训练
作者：Subhankar Ghosh
机构*：Indian Institute of Science
备注：7pages, 10 figures
链接：https://arxiv.org/abs/2102.03778

【3】 Adversarial Imaging Pipelines
标题：对抗性成像管道
作者：Buu Phan,Fahim Mannan,Felix Heide
机构*：Algolux, Princeton University, OBJECT: R.V.
链接：https://arxiv.org/abs/2102.03728

【4】 Adversarial example generation with AdaBelief Optimizer and Crop Invariance
标题：基于AdaBelef优化器和裁剪不变性的对抗性实例生成
作者：Bo Yang,Hengwei Zhang,Yuchen Zhang,Kaiyong Xu,Jindong Wang
备注：9pages, 3figures, 7tables
链接：https://arxiv.org/abs/2102.03726

【5】 HGAN: Hybrid Generative Adversarial Network
标题：HGAN：混合产生式对抗性网络
作者：Seyed Mehdi Iranmanesh,Nasser M. Nasrabadi
机构*：West Virginia University
链接：https://arxiv.org/abs/2102.03710

【6】 Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attack
标题：产生式对抗网络的知识产权保护不受歧义攻击
作者：Ding Sheng Ong,Chee Seng Chan,Kam Woh Ng,Lixin Fan,Qiang Yang
机构*： University of Malaya , WeBank Hong Kong University of Science and Technology
备注：Technical report - 16 pages
链接：https://arxiv.org/abs/2102.04362

【7】 Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improve
标题：用于领域泛化的领域对抗神经网络：何时起作用和如何改进
作者：Anthony Sicilia,Xingchen Zhao,Seong Jae Hwang
机构*：Intelligent Systems Program, University of Pittsburgh
链接：https://arxiv.org/abs/2102.03924

【8】 SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation
标题：SPADE：一种黑盒对抗健壮性评估的谱方法
作者：Wuxinlin Cheng,Chenhui Deng,Zhiqiang Zhao,Yaohui Cai,Zhiru Zhang,Zhuo Feng
机构*：Stevens Institute of Technology, Cornell University
链接：https://arxiv.org/abs/2102.03716

【1】 An Efficient Framework for Zero-Shot Sketch-Based Image Retrieval
标题：一种高效的基于Zero-Shot草图的图像检索框架
作者：Osman Tursun,Simon Denman,Sridha Sridharan,Ethan Goan,Clinton Fookes
机构*：Signal Processing, Artificial Intelligence and Vision Technologies (SAIVT), Queensland University of Technology, australia
链接：https://arxiv.org/abs/2102.04016

【1】 Analysis of Latent-Space Motion for Collaborative Intelligence
标题：面向协同智能的潜在空间运动分析
作者：Mateen Ulhaq,Ivan V. Bajić
备注：6 pages, 6 figures, extended version of an IEEE ICASSP 2021 paper
链接：https://arxiv.org/abs/2102.04018

【2】 CMS-LSTM: Context-Embedding and Multi-Scale Spatiotemporal-Expression LSTM for Video Prediction
标题：CMS-LSTM：基于上下文嵌入和多尺度时空表达的视频预测LSTM
作者：Zenghao Chai,Chun Yuan,Zhihui Lin,Yunpeng Bai
机构*：Shenzhen International Graduate School, Tsinghua University, Shenzhen, China, Tsinghua University Beijing, China, Peng Cheng Laboratory, Shenzhen, China
链接：https://arxiv.org/abs/2102.03586

【1】 Improving memory banks for unsupervised learning with large mini-batch, consistency and hard negative mining
标题：大批量、一致性和强负挖掘改进无监督学习记忆库
作者：Adrian Bulat,Enrique Sánchez-Lozano,Georgios Tzimiropoulos
机构*：Samsung AI Cambridge, Cambridge, UK
备注：Accepted at ICASSP 2021
链接：https://arxiv.org/abs/2102.04442

【2】 Points2Vec: Unsupervised Object-level Feature Learning from Point Clouds
标题：Points2Vec：点云的无监督对象级特征学习
作者：Joël Bachmann,Kenneth Blomqvist,Julian Förster,Roland Siegwart
机构*：Mantis Technologies, Autonomous Systems Lab, Swiss Federal Institute of Technology, Zurich, Switzerland
链接：https://arxiv.org/abs/2102.04136

【3】 Self-supervised driven consistency training for annotation efficient histopathology image analysis
标题：用于高效组织病理学图像分析的自监督驱动一致性训练
作者：Chetan L. Srinidhi,Seung Wook Kim,Fu-Der Chen,Anne L. Martel
机构*：Physical Sciences, Sunnybrook Research Institute, Toronto, Canada, University of Toronto, Canada
链接：https://arxiv.org/abs/2102.03897

【4】 A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learning
标题：基于数据扩充和自监督学习的冠状病毒严重度多示例学习框架
作者：Zekun Li,Wei Zhao,Feng Shi,Lei Qi,Xingzhi Xie,Ying Wei,Zhongxiang Ding,Yang Gao,Shangjie Wu,Jun Liu,Yinghuan Shi,Dinggang Shen
备注：To appear in Medical Image Analysis
链接：https://arxiv.org/abs/2102.03837

【5】 Open-World Semi-Supervised Learning
标题：开放世界半监督学习
作者：Kaidi Cao,Maria Brbic,Jure Leskovec
链接：https://arxiv.org/abs/2102.03526

【1】 Online Clustering-based Multi-Camera Vehicle Tracking in Scenarios with overlapping FOVs
标题：重叠视场场景下基于在线聚类的多摄像机车辆跟踪
作者：Elena Luna,Juan C. SanMiguel,Jose M. Martínez,Marcos Escudero-Viñolo
备注：10 pages
链接：https://arxiv.org/abs/2102.04091

【2】 MOTS R-CNN: Cosine-margin-triplet loss for multi-object tracking
标题：MOTS R-CNN：用于多目标跟踪的余弦裕度三重损失
作者：Amit Satish Unde,Renu M. Rameshan
机构*：Indian Institute of Technology, Mandi, India
备注：10 pages, 2 figures
链接：https://arxiv.org/abs/2102.03512

【1】 Two-Step Image Dehazing with Intra-domain and Inter-domain Adaption
标题：基于域内和域间自适应的两步图像去模糊方法
作者：Xin Yi,Bo Ma,Yulin Zhang,Longyao Liu,JiaHao Wu
备注：9 pages, 7 figures
链接：https://arxiv.org/abs/2102.03501

【2】 A self-adaptive and robust fission clustering algorithm via heat diffusion and maximal turning angle
标题：基于热扩散和最大转角的自适应鲁棒裂变聚类算法
作者：Yu Han,Shizhan Lu,Haiyan Xu
机构*： College of Economics and Management, Nanjing University of Aeronautics and Astronautics, Nanjing , P.R., Nanjing University of Science and Technology, Xiaolingwei , Nanjing, P.R. China
备注：11 pages, 8 figures
链接：https://arxiv.org/abs/2102.03794

【1】 A procedure for automated tree pruning suggestion using LiDAR scans of fruit trees
标题：使用果树激光雷达扫描的树木自动修剪建议程序
作者：Fredrik Westling,James Underwood,Mitch Bryson
链接：https://arxiv.org/abs/2102.03700

【1】 TransReID: Transformer-based Object Re-Identification
标题：TransReID：基于Transformer的对象重新识别
作者：Shuting He,Hao Luo,Pichao Wang,Fan Wang,Hao Li,Wei Jiang
机构*：Alibaba Group,Zhejiang University
链接：https://arxiv.org/abs/2102.04378

【2】 AttributeNet: Attribute Enhanced Vehicle Re-Identification
标题：AttributeNet：属性增强型车辆再识别
作者：Rodolfo Quispe,Cuiling Lan,Wenjun Zeng,Helio Pedrini
机构*：Microsoft Corp., One Microsoft Way, Redmond, USA,-, Microsoft Research Asia, Beijing, China, CInstitute of Computing, University of Campinas, Brazil,-
链接：https://arxiv.org/abs/2102.03898
yb体育官方入口

【1】 Iconographic Image Captioning for Artworks
标题：艺术作品的图像化图像字幕
作者：Eva Cetinic
机构*：Rudjer Boskovic Institute, Bijenicka cesta , Zagreb, Croatia
备注：Accepted at Workshop on Fine Art Pattern Extraction and Recognition (FAPER), ICPR, 2020
链接：https://arxiv.org/abs/2102.03942

【1】 The Multi-Temporal Urban Development SpaceNet Dataset
标题：多时相城市发展空间网络数据集
作者：Adam Van Etten,Daniel Hogan,Jesus Martinez-Manso,Jacob Shermeyer,Nicholas Weir,Ryan Lewis
备注：8 pages, 10 figures, 3 tables
链接：https://arxiv.org/abs/2102.04420

【2】 Overhead MNIST: A Benchmark Satellite Dataset
标题：开销MNIST：一个基准卫星数据集
作者：David Noever,Samantha E. Miller Noever
机构*：PeopleTec, Inc., Huntsville, Alabama, USA
链接：https://arxiv.org/abs/2102.04266

【3】 Scalable Robust Graph and Feature Extraction for Arbitrary Vessel Networks in Large Volumetric Datasets
标题：大体量数据集中任意血管网络的可伸缩鲁棒图与特征提取
作者：Dominik Drees,Aaron Scherzinger,René Hägerling,Friedemann Kiefer,Xiaoyi Jiang
链接：https://arxiv.org/abs/2102.03444

【1】 Point-set Distances for Learning Representations of 3D Point Clouds
标题：用于学习三维点云表示的点集距离
作者：Trung Nguyen,Quang-Hieu Pham,Tam Le,Tung Pham,Nhat Ho,Binh-Son Hua
机构*：VinAI Research, Vietnam ,VinUniversity, Vietnam, Singapore University of Technology and Design ,RIKEN AIP, Japan SUniversity of Texas, Austin
链接：https://arxiv.org/abs/2102.04014

【1】 UniFuse: Unidirectional Fusion for 360$^{\circ}$ Panorama Depth Estimation
作者：Hualie Jiang,Zhe Sheng,Siyu Zhu,Zilong Dong,Rui Huang
备注：9 pages; 5 figures; accepted by IEEE Robotics and Automation Letters; Demo: this https URL
链接：https://arxiv.org/abs/2102.03550

【1】 Subjective and Objective Visual Quality Assessment of Textured 3D Meshes
标题：纹理三维网格视觉质量的主客观评价
作者：Jinjiang Guo,Vincent Vidal,Irene Cheng,Anup Basu,Atilla Baskurt,Guillaume Lavoue
链接：https://arxiv.org/abs/2102.03982

【2】 SR-Affine: High-quality 3D hand model reconstruction from UV Maps
标题：SR-仿射：基于UV贴图的高质量3D手模型重建
作者：Ping Chen,Dong Yang,Fangyin Wu,Qin Li,Qingpei Xia,Yong Tan
机构*：IQIYI Inc., AffineNet, SRNet
备注：9 pages, 5 figures
链接：https://arxiv.org/abs/2102.03725

【3】 Object Removal Attacks on LiDAR-based 3D Object Detectors
标题：基于LiDAR的三维目标检测器的目标移除攻击
作者：Zhongyuan Hau,Kenneth T. Co,Soteris Demetriou,Emil C. Lupu
机构*：Imperial College London
备注：Accepted to AutoSec at NDSS 2021
链接：https://arxiv.org/abs/2102.03722
Bsports官网

【1】 Single Run Action Detector over Video Stream -- A Privacy Preserving Approach
标题：视频流上的单次运行动作检测器--一种隐私保护方法
作者：Anbumalar Saravanan,Justin Sanchez,Hassan Ghasemzadeh,Aurelia Macabasco-O'Connell,Hamed Tabkhi
机构*：University of North Carolina Charlotte
链接：https://arxiv.org/abs/2102.03391

【1】 Colorization Transformer
标题：彩色化Transformer
作者：Manoj Kumar,Dirk Weissenborn,Nal Kalchbrenner
机构*：Google Research, Brain Team
备注：ICLR 2021 Camera Ready. See this https URL for more details
链接：https://arxiv.org/abs/2102.04432

【2】 End-to-end Generative Zero-shot Learning via Few-shot Learning
标题：基于少点学习的端到端产生式零点学习
作者：Georgios Chochlakis,Efthymios Georgiou,Alexandros Potamianos
备注：12 pages, 3 figures, 6 tables
链接：https://arxiv.org/abs/2102.04379

【3】 Counting and Locating High-Density Objects Using Convolutional Neural Network
标题：基于卷积神经网络的高密度物体计数与定位
作者：Mauro dos Santos de Arruda,Lucas Prado Osco,Plabiany Rodrigo Acosta,Diogo Nunes Gonçalves,José Marcato Junior,Ana Paula Marques Ramos,Edson Takashi Matsubara,Zhipeng Luo,Jonathan Li,Jonathan de Andrade Silva,Wesley Nunes Gonçalves
机构*：Federal University of Mato Grosso do Sul, University of Western Sao Paulo, Campo Grande, MS, Brazil, Presidente Prudente, SP, Brazil, mauro. arrudaOufms.br, D Diogo Nunes Goncalves, D Jose Marcato Junior, Xiamen University, University of Waterloo, Xiamen,FJ,China, Waterloo, ON, Canada, edsontmofacom.ufms.br, Wesley Nunes Goncalves, ionathan, andradeufms,b, wesley, goncalyesQufms, br
备注：15 pages, 10 figures, 8 tables
链接：https://arxiv.org/abs/2102.04366

【4】 Multi-level Distance Regularization for Deep Metric Learning
标题：用于深度度量学习的多级距离正则化方法
作者：Yonghyun Kim,Wonpyo Park
机构*：AI Lab, Kakao Enterprise, Kakao Corp.
备注：Accepted to AAAI 2021
链接：https://arxiv.org/abs/2102.04223

【5】 APS: A Large-Scale Multi-Modal Indoor Camera Positioning System
标题：APS：一种大规模多模室内摄像机定位系统
作者：Ali Ghofrani,Rahil Mahdian Toroghi,Seyed Mojtaba Tabatabaie
机构*：Iran Broadcasting University (IRIBU), Tehran,Iran, CEOCTO at Alpha Reality, ARVR Solution Company, alighofraniQiribu.ac.ir
备注：15 pages, 11 figures, MedPRAI 2020
链接：https://arxiv.org/abs/2102.04139

【6】 OV$^{2}$SLAM : A Fully Online and Versatile Visual SLAM for Real-Time Applications
标题：OV$^{2}$SLAM：面向实时应用程序的完全在线且功能全面的Visual SLAM
作者：Maxime Ferrera,Alexandre Eudes,Julien Moras,Martial Sanfourche,Guy Le Besnerais
备注：Accepted for publication in IEEE Robotics and Automation Letters (RA-L). Code is available at : \url{https://github.com/ov2slam/ov2slam}
链接：https://arxiv.org/abs/2102.04060

【7】 In-game Residential Home Planning via Visual Context-aware Global Relation Learning
标题：基于视觉情境感知全球关系学习的游戏中住宅家居规划
作者：Lijuan Liu,Yin Yang,Yi Yuan,Tianjia Shao,He Wang,Kun Zhou
机构*：Clemson University, State Key Lab of CAD&CG, Zhejiang University ,Leeds University
链接：https://arxiv.org/abs/2102.04035

【8】 A Hybrid Bandit Model with Visual Priors for Creative Ranking in Display Advertising
标题：展示广告创意排名的视觉先验混合BANDIT模型
作者：Shiyao Wang,Qi Liu,Tiezheng Ge,Defu Lian,Zhiqiang Zhang
机构*：Alibaba Group, University of Science and Technology, Beijing, China, of China, Hefei,China, Hefei, China
备注：To be published in the International World Wide Web Conference (WWW) 2021
链接：https://arxiv.org/abs/2102.04033

【9】 Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch
标题：从头开始学习N：M细粒度结构化稀疏神经网络
作者：Aojun Zhou,Yukun Ma,Junnan Zhu,Jianbo Liu,Zhijie Zhang,Kun Yuan,Wenxiu Sun,Hongsheng Li
机构*： Sensetime,CUHK-Sensetime Joint Lab, CUHK,Northwestern University, ANLPR, CASIA
备注：ICLR2021
链接：https://arxiv.org/abs/2102.04010

【10】 Identifying the Origin of Finger Vein Samples Using Texture Descriptors
标题：利用纹理描述子识别手指静脉样本的来源
作者：Babak Maser,Andreas Uhl
机构*：Multimedia Signal Processing, & Security Lab, University of Salzburg, AUSTRIA
链接：https://arxiv.org/abs/2102.03992

【11】 Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning
标题：局部胜于全部：重温微调策略的几次学习
作者：Zhiqiang Shen,Zechun Liu,Jie Qin,Marios Savvides,Kwang-Ting Cheng
机构*：Carnegie Mellon University ,Hong Kong University of Science and Technology, Inception Institute of Artificial Intelligence
备注：AAAI 2021. A search based fine-tuning strategy for few-shot learning
链接：https://arxiv.org/abs/2102.03983

【12】 Single-Shot Cuboids: Geodesics-based End-to-end Manhattan Aligned Layout Estimation from Spherical Panoramas
标题：单炮长方体：球面全景图中基于测地线的曼哈顿端到端对齐布局估计
作者：Nikolaos Zioulis,Federico Alvarez,Dimitrios Zarpalas,Petros Daras
机构*：Centre for Research and Technology Hellas Universidad Politecnica de Madrid, Universidad Politecnica de madrid
链接：https://arxiv.org/abs/2102.03939

【13】 Machine Learning Methods for Histopathological Image Analysis: A Review
标题：组织病理学图像分析的机器学习方法综述
作者：Jonathan de Matos,Steve Tsham Mpinda Ataky,Alceu de Souza Britto Jr.,Luiz Eduardo Soares de Oliveira,Alessandro Lameiras Koerich
机构*：Ecole de Technologie Superieure, Universite du Quebec, Montreal, QC, Canada;, Universidade Estadual de Ponta Grossa, Ponta Grossa,pr, Brazil, Received: date; Accepted: date; Published: date
备注：45 pages. arXiv admin note: text overlap with arXiv:1904.07900
链接：https://arxiv.org/abs/2102.03889

【14】 Sill-Net: Feature Augmentation with Separated Illumination Representation
标题：窗台网：基于分离光照表示的特征增强
作者：Haipeng Zhang,Zhong Cao,Ziang Yan,Changshui Zhang
链接：https://arxiv.org/abs/2102.03539

【15】 IC Networks: Remodeling the Basic Unit for Convolutional Neural Networks
标题：IC网络：重塑卷积神经网络的基本单元
作者：Junyi An,Fengshan Liu,Jian Zhao,Furao Shen
机构*：Nanjing University, Nanjing, China
备注：7 pages, 3 figure
链接：https://arxiv.org/abs/2102.03495

【16】 Learning Audio-Visual Correlations from Variational Cross-Modal Generation
标题：从变分跨模态生成中学习视听相关性
作者：Ye Zhu,Yu Wu,Hugo Latapie,Yi Yang,Yan Yan
机构*： Illinois Institute of Technology, USA, ReLER, University of Technology Sydney, Australia, Cisco, USA
备注：ICASSP 2021
链接：https://arxiv.org/abs/2102.03424

【17】 Unlocking Pixels for Reinforcement Learning via Implicit Attention
标题：基于内隐注意的强化学习解锁方法
作者：Krzysztof Choromanski,Deepali Jain,Jack Parker-Holder,Xingyou Song,Valerii Likhosherstov,Anirban Santara,Aldo Pacchiano,Yunhao Tang,Adrian Weller
链接：https://arxiv.org/abs/2102.04353

【18】 Segmentasi Citra Menggunakan Metode Watershed Transform Berdasarkan Image Enhancement Dalam Mendeteksi Embrio Telur
标题：Segmentasi Citra Mengganakan Metode分水岭变换Berdasarkan图像增强Dalam Mendeteksi Embrio Telur
作者：Shoffan Saifullah
机构*：Universitas Pembangunan Nasional Veteran Yogyakarta, Kata Kunci, Abstrak, Image Processing, Image processing dapat diterapkan dalam proses deteksi embrio telur. Proses deteksi, Deteksi Embrio Telur, embrio telur dilakukan dengan menggunakan proses segmentasi, yang membagi citra, CLAHE-HE, Watershed, sesuai dengan daerah yang dibagi. Proses ini memerlukan perbaikan citra yang diproses, Transform, untuk memperoleh hasil optimal. Penelitian ini akan menganalisis deteksi embrio telur, berdasarkan image processing dengan image enhancement dan konsep segmentasi, menggunakan metode watershed transform Image enhacement pada preprocessing, dalam perbaikan citra menggunakan kombinasi metode Contrast Limited Adaptive, Histogram Equalization (CLAHE) dan Histogram Equalization (HE). Citra grayscale telur, diperbaiki dengan menggunakan metode CLAHE, dan hasilnya diproses kembali dengan, menggunakan HE. Hasil perbaikan citra menunjukkan bahwa metode kombinasi claHe, HE memberikan gambar secara jelas daerah objek citra telur yang memiliki embrio.
备注：8 pages, 6 figures
链接：https://arxiv.org/abs/2102.04202

【19】 Switching Variational Auto-Encoders for Noise-Agnostic Audio-visual Speech Enhancement
标题：用于噪声不可知视听语音增强的切换变分自动编码器
作者：Mostafa Sadeghi,Xavier Alameda-Pineda
机构*：Inria Nancy Grand-Est,Inria Grenoble Rhone-Alpes Univ. Grenoble Alpes, France
备注：2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
链接：https://arxiv.org/abs/2102.04144

【20】 The Autonomous Siemens Tram
标题：西门子自主有轨电车
作者：Andrew W. Palmer,Albi Sema,Wolfram Martens,Peter Rudolph,Wolfgang Waizenegger
备注：6 pages, presented at the 2020 International Conference on Intelligent Transportation Systems (ITSC)
链接：https://arxiv.org/abs/2102.04034

【21】 IDOL: Inertial Deep Orientation-Estimation and Localization
标题：Idol：惯性深度定向-估计与定位
作者：Scott Sun,Dennis Melamed,Kris Kitani
机构*：Carnegie Mellon University
备注：To be published in AAAI 2021
链接：https://arxiv.org/abs/2102.04024

【22】 Mimetic Neural Networks: A unified framework for Protein Design and Folding
标题：模拟神经网络：蛋白质设计和折叠的统一框架
作者：Moshe Eliasof,Tue Boesen,Eldad Haber,Chen Keasar,Eran Treister
链接：https://arxiv.org/abs/2102.03881

【23】 MULLS: Versatile LiDAR SLAM via Multi-metric Linear Least Square
标题：考虑：通过多度量线性最小二乘实现多功能LiDAR SLAM
作者：Yue Pan,Pengchuan Xiao,Yujie He,Zhenlei Shao,Zesong Li
备注：Codes: this https URL
链接：https://arxiv.org/abs/2102.03771

【24】 Predicting Eye Fixations Under Distortion Using Bayesian Observers
标题：利用贝叶斯观测器预测畸变情况下的眼睛注视
作者：Zhengzhong Tu
机构*：University of Texas at Austin
备注：18 pages, single-column. Project report
链接：https://arxiv.org/abs/2102.03675

机器翻译，仅供参考；“机构”信息仅供参考