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 [检测分类相关]：
【1】 AutoSelect: Automatic and Dynamic Detection Selection for 3D Multi-Object Tracking
标题：自动选择：三维多目标跟踪的自动动态检测选择
作者：Xinshuo Weng,Kris Kitani
链接：https://arxiv.org/abs/2012.05894
【2】 SPAA: Stealthy Projector-based Adversarial Attacks on Deep Image Classifiers
标题：SPAA：基于家用投影仪的隐身攻击深度图像分类器
作者：Bingyao Huang,Haibin Ling
机构*：Stony Brook University
链接：https://arxiv.org/abs/2012.05858
【3】 Sylvester Matrix Based Similarity Estimation Method for Automation of Defect Detection in Textile Fabrics
标题：基于Sylvester矩阵的织物疵点自动检测相似度估计方法
作者：R. M. L. N. Kumari,G. A. C. T. Bandara,Maheshi B. Dissanayake
机构*：Submitted to: Journal of Sensors, Hindawi
备注：Journal of Sensors, Hindawi
链接：https://arxiv.org/abs/2012.05800
【4】 Demystifying Pseudo-LiDAR for Monocular 3D Object Detection
标题：用于单目三维目标检测的伪LiDAR去神秘化
作者：Andrea Simonelli,Samuel Rota Bulò,Lorenzo Porzi,Peter Kontschieder,Elisa Ricci
机构*：University of Trento, Fondazione Bruno Kessler,Facebook
链接：https://arxiv.org/abs/2012.05796
【5】 OneNet: Towards End-to-End One-Stage Object Detection
标题：OneNet：走向端到端的一级目标检测
作者：Peize Sun,Yi Jiang,Enze Xie,Zehuan Yuan,Changhu Wang,Ping Luo
机构*：IThe University of Hong Kong ,ByteDance AI Lab
链接：https://arxiv.org/abs/2012.05780
【6】 R-AGNO-RPN: A LIDAR-Camera Region Deep Network for Resolution-Agnostic Detection
标题：R-AgNO-RPN：一种用于分辨率不可知检测的LIDAR相机区域深度网络
作者：Ruddy Théodose,Dieumet Denis,Thierry Chateau,Vincent Frémont,Paul Checchin
链接：https://arxiv.org/abs/2012.05740
【7】 An Analysis of Deep Object Detectors For Diver Detection
标题：潜水员探测中的深部目标探测器分析
作者：Karin de Langis,Michael Fulton,Junaed Sattar
机构*：December
备注：14 pages, submitted for ICRA 21
链接：https://arxiv.org/abs/2012.05701
【8】 Investigating Bias in Image Classification using Model Explanations
标题：利用模型解释研究图像分类中的偏差
作者：Schrasing Tong,Lalana Kagal
链接：https://arxiv.org/abs/2012.05463
【9】 A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data
标题：一种无源数据的无监督领域自适应目标检测免费午餐
作者：Xianfeng Li,Weijie Chen,Di Xie,Shicai Yang,Peng Yuan,Shiliang Pu,Yueting Zhuang
机构*： South China University of Technology Hikvision Research Institute , Zhejiang University
备注：accepted by AAAI2021
链接：https://arxiv.org/abs/2012.05400
【10】 3D attention mechanism for fine-grained classification of table tennis strokes using a Twin Spatio-Temporal Convolutional Neural Networks
标题：基于双时空卷积神经网络的乒乓球笔划细粒度分类三维注意机制
作者：Pierre-Etienne Martin,Jenny Benois-Pineau,Renaud Péteri,Julien Morlier
机构*：Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR , F-, Talence, France, FMIA, University of La Rochelle, La Rochelle, France, FIMS, University of Bordeaux, Talence, France
备注：None
链接：https://arxiv.org/abs/2012.05342
【11】 3D Bounding Box Detection in Volumetric Medical Image Data: A Systematic Literature Review
标题：体医学图像数据中三维包围盒检测的系统文献综述
作者：Daria Kern,Andre Mastmeyer
机构*：Aalen University, Aalen, Germany
备注：10 pages, 5 figures, 1 table
链接：https://arxiv.org/abs/2012.05745
【12】 Detection of Covid-19 Patients with Convolutional Neural Network Based Features on Multi-class X-ray Chest Images
标题：基于多类X线胸片特征的卷积神经网络检测冠状病毒患者
作者：Ali Narin
机构*：Zonguldak Bulent Ecevit University, Zonguldak, Turkey
备注：Presented at 2020 Medical Technologies Congress, TIPTEKNO2020 (IEEE)
链接：https://arxiv.org/abs/2012.05525
[分割/语义相关]：
【1】 HRCenterNet: An Anchorless Approach to Chinese Character Segmentation in Historical Documents
标题：HRCenterNet：一种面向历史文献的无锚式中文分词方法
作者：Chia-Wei Tang,Chao-Lin Liu,Po-Sen Chiu
机构*：National Chengchi University, Taipei, Taiwan
链接：https://arxiv.org/abs/2012.05739
【2】 Exploiting Diverse Characteristics and Adversarial Ambivalence for Domain Adaptive Segmentation
标题：利用不同特征和对抗性矛盾进行领域自适应分割
作者：Bowen Cai,Huan Fu,Rongfei Jia,Binqiang Zhao,Hua Li,Yinghui Xu
机构*：Alibaba group, Institute of Computing Technology, Chinese Academy of Sciences
备注：Accepted to AAAI 2021
链接：https://arxiv.org/abs/2012.05608
【3】 Amodal Segmentation Based on Visible Region Segmentation and Shape Prior
标题：基于可见区域分割和形状先验的非模态分割
作者：Yuting Xiao,Yanyu Xu,Ziming Zhong,Weixin Luo,Jiawei Li,Shenghua Gao
机构*： ShanghaiTech University Shanghai Engineering Research Center of Intelligent Vision and Imaging , Alibaba Group, Institute of High Performance Computing, ASTAR
备注：Accepted by AAAI 2021
链接：https://arxiv.org/abs/2012.05598
【4】 Spatiotemporal Graph Neural Network based Mask Reconstruction for Video Object Segmentation
标题：基于时空图神经网络的掩模重建视频对象分割
作者：Daizong Liu,Shuangjie Xu,Xiao-Yang Liu,Zichuan Xu,Wei Wei,Pan Zhou
机构*：Huazhong University of Science and Technology DEEPROUTE.AI, Columbia University Dalian University of Technology
备注：Accepted by AAAI 2021
链接：https://arxiv.org/abs/2012.05499
【5】 Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding
标题：基于判别嵌入全局相关网络的Few-Shot医学图像分割
作者：Liyan Sun,Chenxin Li,Xinghao Ding,Yue Huang,Guisheng Wang,Yizhou Yu
备注：10 pages, 8 figures
链接：https://arxiv.org/abs/2012.05440
【6】 Multi-Model Learning for Real-Time Automotive Semantic Foggy Scene Understanding via Domain Adaptation
标题：基于领域自适应的实时汽车语义雾化场景理解多模型学习
作者：Naif Alshammari,Samet Akcay,Toby P. Breckon
机构*：Durham University, Durham, UK, Majma'ah University, Majma'ah, KSA, COSMONiO, Durham, UK
备注：arXiv admin note: substantial text overlap with arXiv:1909.07697
链接：https://arxiv.org/abs/2012.05320
【7】 ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
标题：VIP-DeepLab：利用深度感知视频全景分割学习视觉感知
作者：Siyuan Qiao,Yukun Zhu,Hartwig Adam,Alan Yuille,Liang-Chieh Chen
机构*：Johns Hopkins University ,Google Research
备注：Video: this https URL GitHub: this https URL
链接：https://arxiv.org/abs/2012.05258
【8】 Learning Tubule-Sensitive CNNs for Pulmonary Airway and Artery-Vein Segmentation in CT
标题：用于CT肺动脉和动静脉分割的学习小管敏感CNN
作者：Yulei Qin,Hao Zheng,Yun Gu,Xiaolin Huang,Jie Yang,Lihui Wang,Feng Yao,Yue-Min Zhu,Guang-Zhong Yang
备注：14 pages, submitted to IEEE TMI
链接：https://arxiv.org/abs/2012.05767
【9】 Effect of the regularization hyperparameter on deep learning-based segmentation in LGE-MRI
标题：LGE-MRI中正则化超参数对深度学习分割的影响
作者：Olivier Rukundo
机构*：Lund University, Lund, Sweden
备注：5 pages, 2 figures
链接：https://arxiv.org/abs/2012.05661
【10】 Unsupervised Adversarial Domain Adaptation For Barrett's Segmentation
标题：基于Barrett分割的无监督对敌域自适应算法
作者：Numan Celik,Soumya Gupta,Sharib Ali,Jens Rittscher
机构*：Institute of Biomedical Engineering (IBME), University of Oxford, Oxford, UK, NIHR Oxford Biomedical Research Centre Oxford University Hospitals NHS Foundation Trust, Oxford, Oxfordshire, UK, University of Oxford, John Radcliffe Hospital, Oxford, UK
备注：5 pages, 3 figures, conference paper
链接：https://arxiv.org/abs/2012.05316
[人脸相关]：
【1】 Independent Sign Language Recognition with 3D Body, Hands, and Face Reconstruction
标题：具有3D身体、手和面部重建的独立手语识别
作者：Agelos Kratimenos,Georgios Pavlakos,Petros Maragos
机构*： Athens, Greece, California, USA, Robot Perception and Interaction Unit, Athena Research Center, Maroussi, Greece
备注：Submitted to ICASSP 2021
链接：https://arxiv.org/abs/2012.05698
【2】 Topology-Adaptive Mesh Deformation for Surface Evolution, Morphing, and Multi-View Reconstruction
标题：用于曲面演化、变形和多视图重建的拓扑自适应网格变形
作者：Andrei Zaharescu,Edmond Boyer,Radu Horaud
备注：None
链接：https://arxiv.org/abs/2012.05536
【3】 Vulnerability Analysis of Face Morphing Attacks from Landmarks and Generative Adversarial Networks
标题：基于地标和生成性对抗网络的人脸变形攻击脆弱性分析
作者：Eklavya Sarkar,Pavel Korshunov,Laurent Colbois,Sébastien Marcel
机构*：Idiap Research Institute, Martigny, Switzerland
备注：Submitted to ICASSP 2021
链接：https://arxiv.org/abs/2012.05344
【4】 Facial expressions can detect Parkinson's disease: preliminary evidence from videos collected online
标题：面部表情可以检测出帕金森氏症：来自网上收集的视频的初步证据
作者：Mohammad Rafayet Ali,Taylor Myers,Ellen Wagner,Harshil Ratnu,E. Ray Dorsey,Ehsan Hoque
机构*：Postdoctoral Associate, Computer Science, University of Rochester, Research Coordinator, Center for Health Technology, UX Specialist, Undergraduate Researcher
链接：https://arxiv.org/abs/2012.05373
[GAN/对抗式/生成式相关]：
【1】 Geometric Adversarial Attacks and Defenses on 3D Point Clouds
标题：三维点云的几何对抗攻击与防御
作者：Itai Lang,Uriel Kotlicki,Shai Avidan
机构*：Tel Aviv University
链接：https://arxiv.org/abs/2012.05657
【2】 SSD-GAN: Measuring the Realness in the Spatial and Spectral Domains
标题：SSD-GaN：空间域和谱域的真实性测量
作者：Yuanqi Chen,Ge Li,Cece Jin,Shan Liu,Thomas Li
机构*：Peking University , Peng Cheng Laboratory, Advanced Institute of Information Technology, Peking University , Tencent America
备注：Accepted to AAAI 2021. Code: this https URL
链接：https://arxiv.org/abs/2012.05535
【3】 GAN Steerability without optimization
标题：未经优化的GaN操纵性
作者：Nurit Spingarn-Eliezer,Ron Banner,Tomer Michaeli
机构*：Habana Labs-An Intel company, Caesarea, Israel, Technion-Israel Institute of Technology, Haifa, Israel
链接：https://arxiv.org/abs/2012.05328
【4】 Composite Adversarial Attacks
标题：复合对抗性攻击
作者：Xiaofeng Mao,Yuefeng Chen,Shuhui Wang,Hang Su,Yuan He,Hui Xue
机构*： Alibaba Group, Inst. of Comput. Tech., CAS, Tsinghua University
备注：To appear in AAAI 2021, code will be released later
链接：https://arxiv.org/abs/2012.05434
[行为/时空/光流/姿态/运动]：
【1】 iNeRF: Inverting Neural Radiance Fields for Pose Estimation
标题：iNeRF：用于位姿估计的反演神经辐射场
作者：Lin Yen-Chen,Pete Florence,Jonathan T. Barron,Alberto Rodriguez,Phillip Isola,Tsung-Yi Lin
机构*：Google Research, Massachusetts Institute of Technology, t=o, Observed Image Iterative Pose Estimation, Pose Estimation Results:, wUnknown Pose wNeRF Model, Overlaid NeRF Rendering and Observed Image
备注：Website: this http URL
链接：https://arxiv.org/abs/2012.05877
【2】 Enhancing Human Pose Estimation in Ancient Vase Paintings via Perceptually-grounded Style Transfer Learning
标题：基于感知的风格迁移学习增强古花瓶画中的人体姿态估计
作者：Prathmesh Madhu,Angel Villar-Corrales,Ronak Kosti,Torsten Bendschus,Corinna Reinhardt,Peter Bell,Andreas Maier,Vincent Christlein
机构*：Pattern Recognition Lab,Institut fur Klassische Archaologie,Institut fur Kunstgeschichte, Friedrich-Alexander-Universitat Erlangen-Nurnberg, equal contribution
备注：Link to the repository containing the code to reproduce the experiments. For further details, please read the README. Link: this https URL
链接：https://arxiv.org/abs/2012.05616
【3】 Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes
标题：三维场景中三维人体长期运动与交互的合成
作者：Jiashun Wang,Huazhe Xu,Jingwei Xu,Sifei Liu,Xiaolong Wang
机构*：UC San Diego, UC Berkeley, Shanghai Jiao Tong University NVIDIA
链接：https://arxiv.org/abs/2012.05522
【4】 Developing Motion Code Embedding for Action Recognition in Videos
标题：开发用于视频动作识别的运动代码嵌入
作者：Maxat Alibayev,David Paulius,Yu Sun
机构*：University of South Florida, Tampa, Florida, United States of America
备注：Accepted by 25th International Conference on Pattern Recognition (ICPR2020)
链接：https://arxiv.org/abs/2012.05438
[跟踪相关]：
【1】 MO-LTR: Multiple Object Localization, Tracking, and Reconstruction from Monocular RGB Videos
标题：MO-LTR：单目RGB视频的多目标定位、跟踪和重建
作者：Kejie Li,Hamid Rezatofighi,Ian Reid
链接：https://arxiv.org/abs/2012.05360
[迁移学习/domain/主动学习/自适应]：
【1】 Competitive Simplicity for Multi-Task Learning for Real-Time Foggy Scene Understanding via Domain Adaptation
标题：领域自适应实时雾场景理解多任务学习的好胜简单性
作者：Naif Alshammari,Samet Akcay,Toby P. Breckon
机构*：Durham University, Durham, UK, Majma'ah University, Majma'ah, KSA, COSMONiO, Durham, UK
链接：https://arxiv.org/abs/2012.05304
[Re-id相关]：
【1】 One for More: Selecting Generalizable Samples for Generalizable ReID Model
标题：一台或多个：可推广Reid模型的可推广样本选择
作者：Enwei Zhang,Xinyang Jiang,Hao Cheng,Ancong Wu,Fufu Yu,Ke Li,Xiaowei Guo,Feng Zheng,Wei-Shi Zheng,Xing Sun
机构*： Tencent Youtu Lab, Shanghai, China, Sun Yat-sen University, Shenzhen, China, Southern University of Science and Technology, Shenzhen, China
链接：https://arxiv.org/abs/2012.05475
[视频理解VQA/caption等]：
【1】 Image Captioning with Context-Aware Auxiliary Guidance
标题：具有上下文感知辅助引导的图像字幕
作者：Zeliang Song,Xiaofei Zhou,Zhendong Mao,Jianlong Tan
机构*：Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, University of Chinese Academy of Sciences, Beijing, China, University of Science and Technology of China, Hefei, China
链接：https://arxiv.org/abs/2012.05545
[数据集dataset]：
【1】 Performance Comparison of Balanced and Unbalanced Cancer Datasets using Pre-Trained Convolutional Neural Network
标题：利用预先训练的卷积神经网络对平衡和非平衡癌症数据集性能的比较
作者：Ali Narin
机构*：Zonguldak Bulent Ecevit University, Zonguldak, Turkey
备注：Presented for International Conference on Artificial Intelligence towards Industry 4.0 (ICAII4.0 2020)
链接：https://arxiv.org/abs/2012.05585
[深度depth相关]：
【1】 Robust Consistent Video Depth Estimation
标题：稳健一致的视频深度估计
作者：Johannes Kopf,Xuejian Rong,Jia-Bin Huang
机构*：Facebook, Virginia Tech
备注：Project website: this https URL
链接：https://arxiv.org/abs/2012.05901
【2】 Direct Depth Learning Network for Stereo Matching
标题：用于立体匹配的直接深度学习网络
作者：Hong Zhang,Haojie Li,Shenglun Chen,Tiantian Yan,Zhihui Wang,Guo Lu,Wanli Ouyang
机构*：Dalian University of Technology, Beijing Institute of Technology, The University of Sydney
备注：10 pages,4 figures
链接：https://arxiv.org/abs/2012.05570
[3D/3D重建等相关]：
【1】 DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors
标题：DI-Fusion：具有深度先验的在线隐式三维重建
作者：Jiahui Huang,Shi-Sheng Huang,Haoxuan Song,Shi-Min Hu
机构*：BNRist, Tsinghua University, Beijing
链接：https://arxiv.org/abs/2012.05551
【2】 Auto-MVCNN: Neural Architecture Search for Multi-view 3D Shape Recognition
标题：Auto-MVCNN：多视点三维形状识别的神经结构搜索
作者：Zhaoqun Li,Hongren Wang,Jinxing Li
机构*：The Chinese University of Hong Kong (Shenzhen)
链接：https://arxiv.org/abs/2012.05493
【3】 COVID-MTL: Multitask Learning with Shift3D and Random-weighted Loss for Diagnosis and Severity Assessment of COVID-19
标题：COVID-MTL：基于Shift3D和随机加权损失的多任务学习在冠状病毒诊断和严重程度评估中的应用
作者：Guoqing Bao,Xiuying Wang
机构*：The University of Sydney
备注：This paper is intended to submit to a computer science journal
链接：https://arxiv.org/abs/2012.05509
[其他视频相关]：
【1】 Neural Rate Control for Video Encoding using Imitation Learning
标题：基于模仿学习的神经网络视频编码码率控制
作者：Hongzi Mao,Chenjie Gu,Miaosen Wang,Angie Chen,Nevena Lazic,Nir Levine,Derek Pang,Rene Claus,Marisabel Hechtman,Ching-Han Chiang,Cheng Chen,Jingning Han
机构*：DeepMind Google MIT CSAIL
链接：https://arxiv.org/abs/2012.05339
[其他]：
【1】 Portrait Neural Radiance Fields from a Single Image
标题：单幅图像的人像神经辐射场
作者：Chen Gao,Yichang Shih,Wei-Sheng Lai,Chia-Kai Liang,Jia-Bin Huang
机构*：Virginia Tech, Google
备注：Project webpage: this https URL
链接：https://arxiv.org/abs/2012.05903
【2】 Are Fewer Labels Possible for Few-shot Learning?
标题：有没有可能减少标签，以进行“少机会学习”？
作者：Suichan Li,Dongdong Chen,Yinpeng Chen,Lu Yuan,Lei Zhang,Qi Chu,Nenghai Yu
机构*：University of Science and Technology of China, Microsoft Research
链接：https://arxiv.org/abs/2012.05899
【3】 Full-Glow: Fully conditional Glow for more realistic image generation
标题：全辉光：完全有条件的辉光，可生成更逼真的图像
作者：Moein Sorkhei,Gustav Eje Henter,Hedvig Kjellström
机构*：KTH Royal Institute of Technology, Stockholm, Sweden
备注：17 pages, 12 figures
链接：https://arxiv.org/abs/2012.05846
【4】 Efficient Nonlinear RX Anomaly Detectors
标题：高效的非线性RX异常探测器
作者：José A. Padrón Hidalgo,Adrián Pérez-Suay,Fatih Nar,Gustau Camps-Valls
链接：https://arxiv.org/abs/2012.05799
【5】 Machine Learning Information Fusion in Earth Observation: A Comprehensive Review of Methods, Applications and Data Sources
标题：对地观测中的机器学习信息融合：方法、应用和数据来源综述
作者：S. Salcedo-Sanz,P. Ghamisi,M. Piles,M. Werner,L. Cuadra,A. Moreno-Martínez,E. Izquierdo-Verdiguier,J. Muñoz-Marí,Amirhosein Mosavi,G. Camps-Valls
机构*：Universidad de Alcala, Alcala de Henares, Spain., Helmholtz-Zentrum Dresden-Rossendorf, Helmholtz Institute Freiberg for Resource Technology, Germany., CUniversitat de valencia, Valencia, Spain., Technical University of Munich, Germany., Obuda University, Budapest, Hungary., Oxford Brookes University, Oxford OX,BP, UK, University of Natural Resources and Life Science(BOKU), Vienna, austria
备注：None
链接：https://arxiv.org/abs/2012.05795
【6】 Look Before you Speak: Visually Contextualized Utterances
标题：三思而后行：视觉语境化的话语
作者：Paul Hongsuck Seo,Arsha Nagrani,Cordelia Schmid
机构*：Google Research
链接：https://arxiv.org/abs/2012.05710
【7】 TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
标题：TFPnP：免调谐即插即用近似法及其在反演成像问题中的应用
作者：Kaixuan Wei,Angelica Aviles-Rivero,Jingwei Liang,Ying Fu,Hua Huang,Carola-Bibiane Schönlieb
机构*：Beijing Institute of Technology, Beijing, China, University of Cambridge, Cambridge, United Kingdom, Queen Mary University of London, London United Kingdom, FUYINGOBIT. EDU. CN, Carola-Bibiane Schonlieb
备注：arXiv admin note: substantial text overlap with arXiv:2002.09611
链接：https://arxiv.org/abs/2012.05703
【8】 Increased performance in DDM analysis by calculating structure functions through Fourier transform in time
标题：通过傅立叶变换及时计算结构函数，提高DDM分析的性能
作者：M. Norouzisadeh,G. Cerchiari,F. Croccolo
机构*： Universite de Pau et des Pays de I'Adour, E,S UPPA, CNRS, TOTAL, LFCR UMR, Anglet, France, Institut fur Experimentalphysik, Universitat Innsbruck, Technikerstrasse , Innsbruck, austria, (Dated: December ,)
备注：6 pages, 5 figures
链接：https://arxiv.org/abs/2012.05695
【9】 Lookahead optimizer improves the performance of Convolutional Autoencoders for reconstruction of natural images
标题：前瞻优化器提高卷积自动编码器重建自然图像的性能
作者：Sayan Nag
链接：https://arxiv.org/abs/2012.05694
【10】 Interactive Fusion of Multi-level Features for Compositional Activity Recognition
标题：多层次特征交互融合的构图活动识别
作者：Rui Yan,Lingxi Xie,Xiangbo Shu,Jinhui Tang
机构*：Nanjing University of Science and Technology, China ,Huawei Inc.
链接：https://arxiv.org/abs/2012.05689
【11】 Concept Generalization in Visual Representation Learning
标题：视觉表征学习中的概念概括
作者：Mert Bulent Sariyildiz,Yannis Kalantidis,Diane Larlus,Karteek Alahari
机构*：INAVER LABS Europe, Inria
链接：https://arxiv.org/abs/2012.05649
【12】 Can we detect harmony in artistic compositions? A machine learning approach
标题：我们能察觉到艺术作品中的和谐吗？一种机器学习方法
作者：Adam Vandor,Marie van Vollenhoven,Gerhard Weiss,Gerasimos Spanakis
机构*：Maastricht University, Maastricht, Netherlands, infinity games, www.infinitygames.xzy, maastricht, netherlands, Keywords:, Artistic Compositions, Feature Extraction, Machine Learning
备注：9 pages, ICAART 2021
链接：https://arxiv.org/abs/2012.05633
【13】 Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement
标题：基于Retinex的微光图像增强协作先验结构搜索展开
作者：Risheng Liu,Long Ma,Jiaao Zhang,Xin Fan,Zhongxuan Luo
机构*：Dalian University of Technology, Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province
链接：https://arxiv.org/abs/2012.05609
【14】 An Asynchronous Kalman Filter for Hybrid Event Cameras
标题：一种适用于混合事件摄像机的异步卡尔曼过滤
作者：Ziwei Wang,Yonhon Ng,Cedric Scheerlinck,Robert Mahony
机构*：Systems Theory and Robotics Group Systems Theory and Robotics Group Systems Theory and Robotics Group, Australian National University, ACT, Australia, yonhon.ngoanu. edu.au, December
链接：https://arxiv.org/abs/2012.05590
【15】 Full Matching on Low Resolution for Disparity Estimation
标题：低分辨率全匹配视差估计
作者：Hong Zhang,Shenglun Chen,Zhihui Wang,Haojie Li,Wanli Ouyang
机构*：Dalian University of Technology, The University of Sydney
备注：9pages,5 figures
链接：https://arxiv.org/abs/2012.05586
【16】 Image Matching with Scale Adjustment
标题：基于比例调整的图像匹配
作者：Yves Dufournaud,Cordelia Schmid,Radu Horaud
机构*：INRIA Rhone-Alpes, . Avenue de l'europe, Montbonnot Saint Martin, FRANCE, Computer Vision and Image Understanding, volume,-
备注：None
链接：https://arxiv.org/abs/2012.05582
【17】 Debiased-CAM for bias-agnostic faithful visual explanations of deep convolutional networks
标题：深度卷积网络无偏忠实视觉解释的去偏CAM
作者：Wencan Zhang,Mariella Dimiccoli,Brian Y. Lim
机构*：National University of Singapore, Singapore, Institut de robotica Informatica Industrial CSIC-UPC, Barcelona, spain
链接：https://arxiv.org/abs/2012.05567
【18】 Tensor Composition Net for Visual Relationship Prediction
标题：用于视觉关系预测的张量合成网络
作者：Yuting Qiang,Yongxin Yang,Yanwen Guo,Timothy M. Hospedales
机构*：National Key Laboratory for Software Technology, Nanjing University, Nanjing China, Edinburgh, UK, Samsung AI Research Centre, Cambridge, UK
链接：https://arxiv.org/abs/2012.05473
【19】 Learning Optimization-inspired Image Propagation with Control Mechanisms and Architecture Augmentations for Low-level Vision
标题：基于学习优化的低层视觉控制机制和结构增强图像传播算法
作者：Risheng Liu,Zhu Liu,Pan Mu,Zhouchen Lin,Xin Fan,Zhongxuan Luo
备注：15 pages
链接：https://arxiv.org/abs/2012.05435
【20】 Automatic Diagnosis of Malaria from Thin Blood Smear Images using Deep Convolutional Neural Network with Multi-Resolution Feature Fusion
标题：基于多分辨率特征融合的深层卷积神经网络自动诊断薄血涂片图像疟疾
作者：Tanvir Mahmud,Shaikh Anowarul Fattah
备注：9 Pages, 10 Figures, This Manuscript is under review in Expert Systems
链接：https://arxiv.org/abs/2012.05350
【21】 Convolutional Neural Networks for Multispectral Image Cloud Masking
标题：卷积神经网络在多光谱图像云掩蔽中的应用
作者：Gonzalo Mateo-García,Luis Gómez-Chova,Gustau Camps-Valls
机构*：Image Processing Laboratory (IPL), University of Valencia, Spain
备注：Preprint corresponding to the paper published in 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Fort Worth, TX, USA, pp. 2255-2258
链接：https://arxiv.org/abs/2012.05325
【22】 Flexible Few-Shot Learning with Contextual Similarity
标题：具有上下文相似性的灵活Few-Shot学习
作者：Mengye Ren,Eleni Triantafillou,Kuan-Chieh Wang,James Lucas,Jake Snell,Xaq Pitkow,Andreas S. Tolias,Richard Zemel
机构*：Rice University; Baylor College of Medicine, Baylor College of Medicine; Rice University, University of Toronto; Vector Institute; Canadian Institute for Advanced Research
备注：Technical report, 29 pages
链接：https://arxiv.org/abs/2012.05895
【23】 Large-Scale Generative Data-Free Distillation
标题：大规模创生式无数据蒸馏
作者：Liangchen Luo,Mark Sandler,Zi Lin,Andrey Zhmoginov,Andrew Howard
机构*：Google Research
链接：https://arxiv.org/abs/2012.05578
【24】 Effect of Different Batch Size Parameters on Predicting of COVID19 Cases
标题：不同批次参数对COVID19例预测的影响
作者：Ali Narin,Ziynet Pamuk
机构*： Electrical and Electronics Enginering, Zonguldak Bulent Ecevit University, Zonguldak, Turkey, Biomedical Enginering, Zonguldak Bulent Ecevit University, Zonguldak, Turkey
备注：Presented for International Conference on Artificial Intelligence towards Industry 4.0 (ICAII4.0 2020)
链接：https://arxiv.org/abs/2012.05534
【25】 Deep learning methods for SAR image despeckling: trends and perspectives
标题：SAR图像去斑的深度学习方法：发展趋势与前景
作者：Giulia Fracastoro,Enrico Magli,Giovanni Poggi,Giuseppe Scarpa,Diego Valsesia,Luisa Verdoliva
链接：https://arxiv.org/abs/2012.05508
【26】 Automatic Generation of Interpretable Lung Cancer Scoring Models from Chest X-Ray Images
标题：从胸部X线图像自动生成可解释的肺癌评分模型
作者：Michael J. Horry,Subrata Chakraborty,Biswajeet Pradhan,Manoranjan Paul,Douglas P. S. Gomes,Anwaar Ul-Haq
机构*：Center for Advanced modelling and, Geospatial Information Systems, Systems&, Modelling, IT, University of Technology Sydney, Sydney, NSW , Australia, Machine Vision and Digital Health, (MaViDH), Charles Sturt University, Bathurst, NSW , Australia
备注：9 pages, 11 figures, 4 tables
链接：https://arxiv.org/abs/2012.05447
【27】 Topological Planning with Transformers for Vision-and-Language Navigation
标题：用于视觉和语言导航的变形器拓扑规划
作者：Kevin Chen,Junshen K. Chen,Jo Chuang,Marynel Vázquez,Silvio Savarese
机构*：Stanford University, Marynel vazquez, Yale University
链接：https://arxiv.org/abs/2012.05292
【28】 MetaInfoNet: Learning Task-Guided Information for Sample Reweighting
标题：MetaInfoNet：样本加权的学习任务导向信息
作者：Hongxin Wei,Lei Feng,Rundong Wang,Bo An
机构*：Nanyang Technological University, Singapore
链接：https://arxiv.org/abs/2012.05273
机器翻译，仅供参考；“机构”信息仅供参考 |
用Deepseek满血版问问看
