重大更新！公众号每日速递覆盖arXiv所有方向,涵盖CS|物理|数学|经济|统计|金融|生物|电气等领域。点击查看历史文章列表，可在公众号内订阅#arXiv每日学术速递话题，接收每日推送。点击访问arxivdaily.com每日更新更及时。
计算机视觉与模式识别cs.CV 方向，今日共计66篇
【1】 Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology
标题：自我监督视觉变形器在组织病理学中学习视觉概念
作者：Richard J. Chen,Rahul G. Krishnan
机构*：Department of Biomedical Informatics, Department of Pathology, Harvard Medical School, Department of Computer Science, Department of Laboratory Medicine and Pathobiology, University of Toronto
备注：Learning Meaningful Representations of Life (NeurIPS 2021)
链接：点击下载PDF文件
【2】 Spatiotemporal Transformer Attention Network for 3D Voxel Level Joint Segmentation and Motion Prediction in Point Cloud
标题：基于时空Transformer注意力网络的点云三维体素级联合分割与运动预测
作者：Zhensong Wei,Xuewei Qi,Zhengwei Bai,Guoyuan Wu,Saswat Nayak,Peng Hao,Matthew Barth,Yongkang Liu,Kentaro Oguchi
机构*：and Matthew J. Barth are with the College of Engineering – Center for, Environmental Research and Technology (CE-CERT), University of, LiDAR-based ,D object detection using point cloud data [,]., Following this direction, various types of object detection
备注：Submitted to IV 2022
链接：点击下载PDF文件
【3】 A Multi-scale Transformer for Medical Image Segmentation: Architectures, Model Efficiency, and Benchmarks
标题：一种用于医学图像分割的多尺度转换器：体系结构、模型效率和基准
作者：Yunhe Gao,Mu Zhou,Di Liu,Dimitris Metaxas
机构*： Di Liu and Dimitris Metaxas are with Department ofComputer Science, Rutgers University
链接：点击下载PDF文件
【4】 Tempera: Spatial Transformer Feature Pyramid Network for Cardiac MRI Segmentation
标题：TEMRA：用于心脏MRI分割的空间变换特征金字塔网络
作者：Christoforos Galazis,Huiyi Wu,Zhuoyu Li,Camille Petri,Anil A. Bharath,Marta Varela
机构*： Department of Computing, Imperial College London, UK, National Heart & Lung Institute, Imperial College London, UK, Department of Metabolism,Digestion &Reproduction, Imperial College London, UK, Department of Bioengineering, Imperial College London, UK
Journal-ref：Statistical Atlases and Computational Models of the Heart. Multi-Disease, Multi-View, and Multi-Center Right Ventricular Segmentation in Cardiac MRI Challenge. STACOM 2021. Lecture Notes in Computer Science, vol 13131
链接：点击下载PDF文件
【5】 Spatio-temporal Vision Transformer for Super-resolution Microscopy
标题：用于超分辨率显微镜的时空视觉转换器
作者：Charles N. Christensen,Meng Lu,Edward N. Ward,Pietro Lio,Clemens F. Kaminski
机构*：University of Cambridge, Department of Chemical Engineering and Biotechnology, Laser Analytics Group, Cambridge, UK, University of Cambridge, Department of Computer Science and Technology, Artificial Intelligence Group, Cambridge, UK, –
备注：8 pages, 9 figures. Source code: this https URL
链接：点击下载PDF文件
【1】 Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection
标题：时间感知器：一种通用的任意边界检测体系结构
作者：Jing Tan,Yuhong Wang,Gangshan Wu,Limin Wang
机构*：State Key Laboratory for Novel Software Technology, Nanjing University, China
链接：点击下载PDF文件
【2】 Comprehensive Analysis of the Object Detection Pipeline on UAVs
标题：无人机目标检测流水线的综合分析
作者：Leon Amadeus Varga,Sebastian Koch,Andreas Zell
备注：Submitted IROS22
链接：点击下载PDF文件
【3】 Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection
标题：用于无监督异常检测的全频率通道选择表示法
作者：Yufei Liang,Jiangning Zhang,Shiwei Zhao,Runze Wu,Yong Liu,Shuwen Pan
链接：点击下载PDF文件
【4】 Robots Autonomously Detecting People: A Multimodal Deep Contrastive Learning Method Robust to Intraclass Variations
标题：机器人自主检测人：一种对类内变化鲁棒的多模态深度对比学习方法
作者：Angus Fung,Beno Benhabib,Goldie Nejat
机构*：Robots Autonomously Detecting People: A Multimodal Deep, Contrastive Learning Method Robust to Intraclass Variations, This research is supported by the Natural Sciences and Engineering Research, Council of Canada (NSERC), AGE-WELL Inc., and the Canada Research
链接：点击下载PDF文件
【5】 Towards Targeted Change Detection with Heterogeneous Remote Sensing Images for Forest Mortality Mapping
标题：面向森林死亡制图的异质遥感图像目标变化检测
作者：Jørgen A. Agersborg,Luigi T. Luppino,Stian Normann Anfinsen,Jane Uhd Jepsen
备注：16 pages, 9 figures
链接：点击下载PDF文件
【6】 JOINED : Prior Guided Multi-task Learning for Joint Optic DiscCup Segmentation and Fovea Detection
标题：联合：用于联合视盘杯分割和中心凹检测的先验指导的多任务学习
作者：Huaqing He,Li Lin,Zhiyuan Cai,Xiaoying Tang
机构*： Department of Electrical and Electronic Engineering, Southern University of Science and Technol-, ogy, Shenzhen, China, Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong
备注：16 pages, 3 figures, Published in Medical Imaging with Deep Learning (MIDL) 2022
链接：点击下载PDF文件
【7】 BlazeNeo: Blazing fast polyp segmentation and neoplasm detection
标题：BlazeNeo：快速的息肉分割和肿瘤检测
作者：Nguyen Sy An,Phan Ngoc Lan,Dao Viet Hang,Dao Van Long,Tran Quang Trung,Nguyen Thi Thuy,Dinh Viet Sang
机构*： SANG 1 1Hanoi University of Science and Technology, Vietnam 2Hanoi Medical University, Vietnam 3Institute of Gastroenterology and Hepatology, Vietnam 4University of Medicine and Pharmacy, Hue University
链接：点击下载PDF文件
【1】 Generalizable Person Re-Identification via Self-Supervised Batch Norm Test-Time Adaption
标题：基于自监督批次定额测试时间自适应的可泛化人员再识别
作者：Ke Han,Chenyang Si,Yan Huang,Liang Wang,Tieniu Tan
机构*： Center for Research on Intelligent Perception and Computing, Institute of Automation, Chinese Academy of Sciences, School of Future Technology, University of Chinese Academy of Sciences (UCAS)
链接：点击下载PDF文件
【2】 SwitchHit: A Probabilistic, Complementarity-Based Switching System for Improved Visual Place Recognition in Changing Environments
标题：SwitchHit：一种改进变化环境下视觉位置识别的概率互补切换系统
作者：Maria Waheed,Michael Milford,Klaus McDonald-Maier,Shoaib Ehsan
链接：点击下载PDF文件
【3】 Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generation
标题：渐近均衡损失和自适应特征生成的长尾分类
作者：Zihan Zhang,Xiang Xiang
机构*：School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, China
链接：点击下载PDF文件
【4】 Bridge the Gap between Supervised and Unsupervised Learning for Fine-Grained Classification
标题：弥合监督学习与非监督学习在细粒度分类中的差距
作者：Jiabao Wang,Yang Li,Xiu-Shen Wei,Hang Li,Zhuang Miao,Rui Zhang
机构*： Nanjing University of Science and Technology
备注：12 pages, 7 figures
链接：点击下载PDF文件
【5】 Semi-supervised Deep Learning for Image Classification with Distribution Mismatch: A Survey
标题：半监督深度学习在分布失配图像分类中的研究进展
作者：Saul Calderon-Ramirez,Shengxiang Yang,David Elizondo
备注：Submission to IEEE Transactions on AI
链接：点击下载PDF文件
【6】 Simultaneous Semantic and Instance Segmentation for Colon Nuclei Identification and Counting
标题：用于结肠细胞核识别和计数的语义和实例同时分割
作者：Lihao Liu,Chenyang Hong,Angelica I. Aviles-Rivero,Carola-Bibiane Schönlieb
机构*：Department of Applied Mathematics, University of Cambridge, Cambridge, UK, Department of Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong (SAR), th Carola-Bibiane Sch¨onlieb
备注：2 pages
链接：点击下载PDF文件
【7】 One Model is All You Need: Multi-Task Learning Enables Simultaneous Histology Image Segmentation and Classification
标题：一个模型就是您需要的全部：多任务学习支持同时进行组织学图像分割和分类
作者：Simon Graham,Quoc Dang Vu,Mostafa Jahanifar,Fayyaz Minhas,David Snead,Nasir Rajpoot
机构*：Department of Computer Science, University of Warwick, UK, Department of Pathology, University Hospitals Coventry and Warwickshire NHS Trust, UK, Histofy Ltd, UK
链接：点击下载PDF文件
【8】 Separable-HoverNet and Instance-YOLO for Colon Nuclei Identification and Counting
标题：可分离HoverNet和Instance-YOLO在结肠细胞核识别和计数中的应用
作者：Chunhui Lin,Liukun Zhang,Lijian Mao,Min Wu,Dong Hu
机构*：Research and Development center, Zhejiang Dahua Technology Co., Ltd, Hangzhou, Zhejiang, China, Hangzhou, Zhengjiang, China
备注：arXiv admin note: text overlap with arXiv:2111.14485 by other authors
链接：点击下载PDF文件
【9】 Nuclear Segmentation and Classification Model with Imbalanced Classes for CoNiC Challenge
标题：二次曲线挑战的带不平衡类的核分割与分类模型
作者：Jijun Cheng,Xipeng Pan,Feihu Hou,Bingchao Zhao,Jiatai Lin,Zhenbing Liu,Zaiyi Liu,Chu Han
机构*： TIA lab from WarwickUniversity organized a nuclear segmentation and classificationchallenge (CoNiC) for H&E stained histopathology images incolorectal cancer based on the Lizard dataset [ 1]
链接：点击下载PDF文件
【1】 A unified 3D framework for Organs at Risk Localization and Segmentation for Radiation Therapy Planning
标题：放射治疗规划中危险器官定位与分割的统一三维框架
作者：Fernando Navarro,Guido Sasahara,Suprosanna Shit,Ivan Ezhov,Jan C. Peeken,Stephanie E. Combs,Bjoern H. Menze
机构*：Department of Informatics, Technical University of Munich, Germany, Center for Translational Cancer Research (TranslaTUM), Klinikum rechts der Isar, Germany, Department of Radio Oncology and Radiation Therapy, Klinikum rechts der Isar, Munich, Germany
链接：点击下载PDF文件
【2】 Boundary Corrected Multi-scale Fusion Network for Real-time Semantic Segmentation
标题：用于实时语义分割的边界校正多尺度融合网络
作者：Tianjiao Jiang,Yi Jin,Tengfei Liang,Xu Wang,Yidong Li
机构*：School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China
备注：5 pages, 3 figures
链接：点击下载PDF文件
【3】 Understanding the Challenges When 3D Semantic Segmentation Faces Class Imbalanced and OOD Data
标题：理解3D语义分割面对类不平衡和面向对象数据的挑战
作者：Yancheng Pan,Fan Xie,Huijing Zhao
机构*： Peking University
链接：点击下载PDF文件
【4】 Local and Global GANs with Semantic-Aware Upsampling for Image Generation
标题：基于语义感知上采样的局部和全局GANS图像生成
作者：Hao Tang,Ling Shao,Philip H. S. Torr,Nicu Sebe
机构*： Torr is with the Department of Engineering Science
备注：Accepted to TPAMI, an extended version of a paper published in CVPR 2020. arXiv admin note: substantial text overlap with arXiv:1912.12215
链接：点击下载PDF文件
【1】 Beam-Shape Effects and Noise Removal from THz Time-Domain Images in Reflection Geometry in the 0.25-6 THz Range
标题：0.25-6THz反射几何中THz时域图像的波束形状效应和噪声去除
作者：Marina Ljubenovic,Alessia Artesani,Stefano Bonetti,Arianna Traviglia
机构*：Stefano Bonetti is with the Department of Molecular Sciences and Nanosys-tems, Ca’Foscari University of Venice, Italy and the Department ofPhysics, Stockholm University
备注：This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible
链接：点击下载PDF文件
【1】 CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding
标题：CrossPoint：三维点云理解的自监督跨模态对比学习
作者：Mohamed Afham,Isuru Dissanayake,Dinithi Dissanayake,Amaya Dharmasiri,Kanchana Thilakarathna,Ranga Rodrigo
机构*：†Dept. of Electronic and Telecommunication Engineering, Univeristy of Moratuwa, Sri Lanka, ‡The University of Sydney
链接：点击下载PDF文件
【2】 Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment
标题：基于检索的多粒度对齐无监督视觉和语言预训练
作者：Mingyang Zhou,Licheng Yu,Amanpreet Singh,Mengjiao Wang,Zhou Yu,Ning Zhang
机构*：Uiversity of California, Davis, Columbia University, Meta AI
备注：First two authors contributed equally. 13 pages, 11 figures
链接：点击下载PDF文件
【3】 ACTIVE:Augmentation-Free Graph Contrastive Learning for Partial Multi-View Clustering
标题：部分多视图聚类的主动无增广图对比学习
作者：Yiming Wang,Dongxia Chang,Zhiqiang Fu,Jie Wen,Yao Zhao
链接：点击下载PDF文件
【4】 Voxelmorph++ Going beyond the cranial vault with keypoint supervision and multi-channel instance optimisation
标题：Voxelmorph++超越头颅穹顶，提供关键点监控和多通道实例优化
作者：Mattias P. Heinrich,Lasse Hansen
机构*：Institute of Medical Informatics, University of L¨ubeck, Germany
备注：10 pages, accepted at WBIR 2022
链接：点击下载PDF文件
【5】 Towards a unified view of unsupervised non-local methods for image denoising: the NL-Ridge approach
标题：统一看待无监督非局部图像去噪方法：NL-Ridge方法
作者：Sébastien Herbreteau,Charles Kervrann
机构*：SERPICO Project-Team, Inria Centre Rennes - Bretagne Atlantique, UMR, CNRS Institut Curie, PSL Research University, Sorbonne Universit´e, France
链接：点击下载PDF文件
【1】 Motion-aware Dynamic Graph Neural Network for Video Compressive Sensing
标题：运动感知动态图神经网络在视频压缩传感中的应用
作者：Ruiying Lu,Ziheng Cheng,Bo Chen,Xin Yuan
链接：点击下载PDF文件
【2】 Adversarial samples for deep monocular 6D object pose estimation
标题：用于深部单目6维目标姿态估计的对抗性样本
作者：Jinlai Zhang,Weiming Li,Shuang Liang,Hao Wang,Jihong Zhu
机构*： Guangxi University, Samsung Research China - Beijing (SRC-B), Tsinghua University
备注：15 pages. arXiv admin note: text overlap with arXiv:2105.14291 by other authors
链接：点击下载PDF文件
【3】 Learning Cross-Video Neural Representations for High-Quality Frame Interpolation
标题：学习用于高质量帧内插的跨视频神经表示
作者：Wentao Shangguan,Yu Sun,Weijie Gan,Ulugbek S. Kamilov
机构*：Department of Computer Science and Engineering, Washington University in St. Louis, MO , USA, Department of Electrical and Systems Engineering, Washington University in St. Louis, MO , USA
链接：点击下载PDF文件
【1】 Towards IID representation learning and its application on biomedical data
标题：面向IID的表征学习及其在生物医学数据中的应用
作者：Jiqing Wu,Inti Zlobec,Maxime Lafarge,Yukun He,Viktor H. Koelzer
机构*： Department of Pathology and Molecular Pathology, University Hospital, University of Zurich, Switzerland., Department of Pathology, University of Bern, Switzerland., Department of Mathematics, City University of Hong Kong, China.
备注：The paper is accepted by MIDL 2022--full paper track
链接：点击下载PDF文件
【2】 MRI-GAN: A Generalized Approach to Detect DeepFakes using Perceptual Image Assessment
标题：MRI-GAN：一种基于知觉图像评估的深裂检测通用方法
作者：Pratikkumar Prajapati,Chris Pollett
机构*： Our goal is to quantify the accuracy of Deep-Fake detection for a variety of natural settings using deep†Department of Computer Science, San José State University
备注：9 pages, 11 figures, 2 tables
链接：点击下载PDF文件
【3】 Deep Learning based Prediction of MSI in Colorectal Cancer via Prediction of the Status of MMR Markers
标题：基于深度学习的MMR标志物状态预测大肠癌MSI
作者：Ruqayya Awan,Mohammed Nimir,Shan E Ahmed Raza,Johannes Lotz,David Snead,Andrew Robison,Nasir M. Rajpoot
机构*：Department of Computer Science, University of Warwick, UK, Department of Pathology, University Hospitals Coventry & Warwickshire, UK, Fraunhofer Institute for Digital Medicine MEVIS, L¨ubeck, Germany, The Alan Turing Institute, London, UK
链接：点击下载PDF文件
【1】 Generative Adversarial Networks
标题：生成性对抗性网络
作者：Gilad Cohen,Raja Giryes
机构*： the counterfeitGilad CohenTel Aviv University, ilRaja GiryesTel Aviv University
链接：点击下载PDF文件
【2】 Towards Creativity Characterization of Generative Models via Group-based Subset Scanning
标题：基于分组子集扫描的产生式模型创造力表征
作者：Celia Cintas,Payel Das,Brian Quanz,Girmaw Abebe Tadesse,Skyler Speakman,Pin-Yu Chen
机构*：IBM Research Africa, Nairobi, Kenya, Yorktown Heights, NY, USA
备注：Under Review at Special Track at IJCAI 2022. arXiv admin note: substantial text overlap with arXiv:2104.00479, arXiv:2105.12479
链接：点击下载PDF文件
【3】 se-Shweshwe Inspired Fashion Generation
标题：Se-Shweshwe启发了时尚一代
作者：Lindiwe Brigitte Malobola,Negar Rostamzadeh,Shakir Mohamed
机构*：University of the Witwatersrand, Google Research, DeepMind
备注：CVPR 2021 Beyond Fairness workshop
链接：点击下载PDF文件
【1】 CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP
标题：CLIP-Gen：带CLIP的文本到图像生成器的无语言训练
作者：Zihao Wang,Wei Liu,Qian He,Xinglong Wu,Zili Yi
机构*：ByteDance Inc., A photo of komodo dragon, A photo of a cute white shetland, sheepdog sitting on grass, A photo of starfish is dancing, A painting of a, Hamster in the anime style, A photo of a pirate dog, walking on the rainy road, A photo of a blue bird
链接：点击下载PDF文件
【1】 Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention
标题：一元成对注意力增强三维点云处理的局部特征学习
作者：Haoyi Xiu,Xin Liu,Weiming Wang,Kyoung-Sook Kim,Takayuki Shinohara,Qiong Chang,Masashi Matsuoka
机构*：Weimin Wang,†, Department of Architecture and, Building Engineering, Tokyo Institute of Technology, Tokyo, Japan, Artificial Intelligence Research Center, AIST, DUT-RU International School of, Information Science and Engineering, Dalian University of Technology
备注：BMVC 2021
链接：点击下载PDF文件
【1】 Preemptive Motion Planning for Human-to-Robot Indirect Placement Handovers
标题：人-机器人间接放置切换的抢占式运动规划
作者：Andrew Choi,Mohammad Khalid Jawed,Jungseock Joo
机构*：edu 2Department of Mechanical and Aerospace Engineering, University ofCalifornia, edu 3Department of Communication
备注：6 pages, 6 figures, to appear in ICRA 2022
链接：点击下载PDF文件
【1】 Descriptellation: Deep Learned Constellation Descriptors for SLAM
标题：描述：SLAM的深度学习星座描述符
作者：Chunwei Xing,Xinyu Sun,Andrei Cramariuc,Samuel Gull,Jen Jen Chung,Cesar Cadena,Roland Siegwart,Florian Tschopp
链接：点击下载PDF文件
【2】 FP-Loc: Lightweight and Drift-free Floor Plan-assisted LiDAR Localization
标题：FP-Loc：轻量级无漂移平面图辅助激光雷达定位
作者：Ling Gao,Laurent Kneip
机构*：after which they can be aligned with the features of a floor 1ShanghaiTech University, 2Shanghai Institute of Microsystem and Infor-mation Technology, 3University of ChineseAcademy of Sciences
Journal-ref：IEEE International Conference on Robotics and Automation (ICRA), 2022
链接：点击下载PDF文件
【3】 Deep Camera Pose Regression Using Pseudo-LiDAR
标题：基于伪激光雷达的深度相机位姿回归
作者：Ali Raza,Lazar Lolic,Shahmir Akhter,Alfonso Dela Cruz,Michael Liut
机构*：UniversityofTorontoMississauga
备注：7 pages, 5 figures, 2 tables
链接：点击下载PDF文件
【1】 Multi-modal Alignment using Representation Codebook
标题：使用表示码本的多模式对齐
作者：Jiali Duan,Liqun Chen,Son Tran,Jinyu Yang,Yi Xu,Belinda Zeng,Chenyang Tao,Trishul Chilimbi
机构*： Amazon, University of Texas at Arlington
链接：点击下载PDF文件
【2】 Multi-Modal Recurrent Fusion for Indoor Localization
标题：多模态递归融合在室内定位中的应用
作者：Jianyuan Yu,Pu Wang,Toshiaki Koike-Akino,Philip V. Orlik
机构*：Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA , USA
备注：5 pages, 4 figures, 1 table
链接：点击下载PDF文件
【1】 ProgressLabeller: Visual Data Stream Annotation for Training Object-Centric 3D Perception
标题：ProgressLabeller：用于训练以对象为中心的三维感知的视觉数据流注释
作者：Xiaotong Chen,Huijie Zhang,Zeren Yu,Stanley Lewis,Odest Chadwicke Jenkins
机构*： Jenkins are withthe Department of Electrical Engineering and Computer Science, andRobotics Institute at the University of Michigan
链接：点击下载PDF文件
【2】 Optimal Transport-based Graph Matching for 3D retinal OCT image registration
标题：基于最优传输的三维视网膜OCT图像配准
作者：Xin Tian,Nantheera Anantrasirichai,Lindsay Nicholson,Alin Achim
机构*：Department of Electrical and Electronic Engineering, University of Bristol, Bristol BS,UB, UK, School of Cellular and Molecular Medicine, Bristol BS,TD, UK
链接：点击下载PDF文件
【3】 Multi-Task Multi-Scale Learning For Outcome Prediction in 3D PET Images
标题：用于三维PET图像结果预测的多任务多尺度学习
作者：Amine Amyar,Romain Modzelewski,Pierre Vera,Vincent Morard,Su Ruan
机构*：General Electric Healthcare, University of Rouen, Rouen, France, Centre Henri Becquerel, General Electectric Healthcare, Buc, France
链接：点击下载PDF文件
【1】 Realtime strategy for image data labelling using binary models and active sampling
标题：基于二值模型和主动采样的图像数据实时标注策略
作者：Ankush Deshmukh,Bhargava B C,A V Narasimhadhan
机构*：Electronics and Communication, NIT Surathkal, Manglore, India, Satya Kumar Vankayala, Networks SW R&D Group, Samsung R&D Institute, Bengaluru, India, Seungil Yoon, Network Business, Samsung Electronics, Suwon, South Korea
链接：点击下载PDF文件
【2】 Exploring Wilderness Using Explainable Machine Learning in Satellite Imagery
标题：利用可解释机器学习在卫星图像中探索荒野
作者：Timo T. Stomberg,Taylor Stone,Johannes Leonhardt,Ribana Roscher
机构*：Institute of Geodesy and Geoinformation, University of Bonn, Germany, Institute for Science and Ethics, University of Bonn, Germany, Data Science in Earth Observation, Technical University of Munich, Germany, corresponding author
链接：点击下载PDF文件
【3】 Affordance Learning from Play for Sample-Efficient Policy Learning
标题：从游戏中获得实惠学习，实现样本高效的政策学习
作者：Jessica Borja-Diaz,Oier Mees,Gabriel Kalweit,Lukas Hermann,Joschka Boedecker,Wolfram Burgard
机构*： All authors are with the University of Freiburg
备注：Accepted at the 2022 IEEE International Conference on Robotics and Automation (ICRA). Videos at this http URL
链接：点击下载PDF文件
【4】 When A Conventional Filter Meets Deep Learning: Basis Composition Learning on Image Filters
标题：当传统的过滤遇到深度学习：基于图像过滤器的基本构图学习
作者：Fu Lee Wang,Yidan Feng,Haoran Xie,Gary Cheng,Mingqiang Wei
机构*：Wei, Received: date Accepted: date
备注：14 pages, 10 figures
链接：点击下载PDF文件
【5】 The Right Spin: Learning Object Motion from Rotation-Compensated Flow Fields
标题：右旋：从旋转补偿流场中学习物体运动
作者：Pia Bideau,Erik Learned-Miller,Cordelia Schmid,Karteek Alahari
机构*：Science of Intelligence, TU Berlin, Berlin, Germany., University of Massachusetts, Governors Dr, Amherst, MA, US., Inria, ´Ecole Normale Sup´erieure, CNRS, PSL Research University, Paris, France.
链接：点击下载PDF文件
【6】 Towards deep learning-powered IVF: A large public benchmark for morphokinetic parameter prediction
标题：走向深度学习驱动的体外受精：形态动力学参数预测的大型公共基准
作者：Tristan Gomez,Magalie Feyeux,Nicolas Normand,Laurent David,Perrine Paul-Gilloteaux,Thomas Fréour,Harold Mouchère
链接：点击下载PDF文件
【1】 Variational Autoencoders Without the Variation
标题：不带变分的变分自动编码器
作者：Gregory A. Daly,Jonathan Eyb体育官方入口. Fieldsend,Gavin Tabor
机构*：College of Engineering, Mathematics and Physical Sciences , Harrison Building, Streatham Campus, University of Exeter , North Park Road , Exeter, UK, EX,QF
备注：11 pages, 7 figures, 3 tables
链接：点击下载PDF文件
【2】 Compliance Challenges in Forensic Image Analysis Under the Artificial Intelligence Act
标题：“人工智能法案”下法医图像分析的合规性挑战
作者：Benedikt Lorch,Nicole Scheler,Christian Riess
机构*：∗IT Security Infrastructures Lab, Friedrich-Alexander-Universit¨at, Erlangen, Germany, †International Criminal Law Research Unit, Friedrich-Alexander-Universit¨at, Erlangen, Germany
链接：点击下载PDF文件
【3】 Technological evaluation of two AFIS systems
标题：两种自动指纹识别系统的技术评价
作者：Marcos Faundez-Zanuy
机构*：Escola Universitaria Politècnica de Mataró, Avda. Puig i Cadafalch ,-, MATARO (BARCELONA) SPAIN
Journal-ref：IEEE Aerospace and Electronic Systems Magazine, vol. 20, no. 4, pp. 13-17, April 2005
链接：点击下载PDF文件
【4】 Efficient Globally-Optimal Correspondence-Less Visual Odometry for Planar Ground Vehicles
标题：高效全局最优的平面地面车辆无对应视觉里程计
作者：Ling Gao,Junyan Su,Jiadi Cui,Xiangchen Zeng,Xin Peng,Laurent Kneip
机构*： and that—as a result—the motionAlltheauthorsarewiththeSchoolofSchoolofIn-formationScienceandTechnology, ShanghaiTechUniversity
Journal-ref：IEEE International Conference on Robotics and Automation (ICRA), 2020
链接：点击下载PDF文件
【5】 How certain are your uncertainties?
标题：你的不确定性有多大？
作者：Luke Whitbread,Mark Jenkinson
机构*： School of Computer Science, The University of Adelaide, Australia, Wellcome Centre for Integrative Neuroimaging, University of Oxford, United, Kingdom
链接：点击下载PDF文件
【6】 Rectifying homographies for stereo vision: analytical solution for minimal distortion
标题：立体视觉中的单应校正：最小失真的解析解
作者：Pasquale Lafiosca,Marta Ceccaroni
机构*：Integrated Vehicle Health Management Centre, Cranfield University, United, School of Aerospace, Cranfield University, United Kingdom
链接：点击下载PDF文件
【7】 Effectiveness of Delivered Information Trade Study
标题：信息传递交易的有效性研究
作者：Matthew Ciolino
机构*：PeopleTec Inc., Huntsville, AL, USA
备注：5 Pages, 3 Figures, 1 Table, 39 References
链接：点击下载PDF文件
【8】 ERF: Explicit Radiance Field Reconstruction From Scratch
标题：ERF：从头开始的显式辐射场重建
作者：Samir Aroudj,Steven Lovegrove,Eddy Ilg,Tanner Schmidt,Michael Goesele,Richard Newcombe
备注：23 pages, 18 figures
链接：点击下载PDF文件
【9】 Full RGB Just Noticeable Difference (JND) Modelling
标题：全RGB仅显著差异(JND)建模
作者：Jian Jin,Dong Yu,Weisi Lin,Lili Meng,Hao Wang,Huaxiang Zhang
备注：13 pages, 8 figures, 8 tables
链接：点击下载PDF文件
机器翻译，仅供参考
重大更新！公众号每日速递覆盖arXiv所有方向,涵盖CS|物理|数学|经济|统计|金融|生物|电气等领域。点击查看历史文章列表，可在公众号内订阅#arXiv每日学术速递话题，接收每日推送。点击访问arxivdaily.com每日更新更及时。
