计算机视觉/图像处理每日论文速递[03.16]

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】 Multiclass Anomaly Detection in GI Endoscopic Images using Optimized Deep One-class Classification in an Imbalanced Dataset
标题：基于非平衡数据集中优化深度单类分类的胃肠道内窥镜图像多类异常检测
作者：Mohammad Reza Mohebbian,Seyed Shahim Vedaei,Khan A. Wahid,Paul Babyn
链接：https://arxiv.org/abs/2103.08508

【2】 S-AT GCN: Spatial-Attention Graph Convolution Network based Feature Enhancement for 3D Object Detection
标题：S-ATGCN：基于空间注意图卷积网络的三维目标检测特征增强
作者：Li Wang,Chenfei Wang,Xinyu Zhang,Tianwei Lan,Jun Li
链接：https://arxiv.org/abs/2103.08439

【3】 Metric Learning for Anti-Compression Facial Forgery Detection
标题：度量学习在人脸防伪检测中的应用
作者：Shenhao Cao,Qin Zou,Xiuqing Mao,Zhongyuan Wang
链接：https://arxiv.org/abs/2103.08397

【4】 3D-FFS: Faster 3D object detection with Focused Frustum Search in sensor fusion based networks
标题：3D-FFS：基于传感器融合的网络中基于聚焦最高点搜索的快速3D目标检测
作者：Aniruddha Ganguly,Tasin Ishmam,Khandker Aftarul Islam,Md Zahidur Rahman,Md. Shamsuzzoha Bayzid
备注：Contains 6 pages and 2 figures. Manuscript submitted to the IEEE International Conference on Intelligent Robots and Systems (IROS) 2021 and is currently pending review
链接：https://arxiv.org/abs/2103.08294

【5】 Boosting ship detection in SAR images with complementary pretraining techniques
标题：基于互补预训练技术的SAR图像舰船检测
作者：Wei Bao,Meiyu Huang,Yaqin Zhang,Yao Xu,Xuejiao Liu,Xueshuang Xiang
链接：https://arxiv.org/abs/2103.08251

【6】 Detecting Human-Object Interaction via Fabricated Compositional Learning
标题：基于构造性成分学习的人-物交互检测
作者：Zhi Hou,Baosheng Yu,Yu Qiao,Xiaojiang Peng,Dacheng Tao
备注：Accepted to CVPR2021
链接：https://arxiv.org/abs/2103.08214

【7】 Geometric Change Detection in Digital Twins using 3D Machine Learning
标题：基于3D机器学习的数字双胞胎几何变化检测
作者：Tiril Sundby,Julia Maria Graham,Adil Rasheed,Mandar Tabib,Omer San
链接：https://arxiv.org/abs/2103.08201

【8】 Detection and Localization of Facial Expression Manipulations
标题：面部表情操作的检测与定位
作者：Ghazal Mazaheri,Amit K. Roy-Chowdhury
链接：https://arxiv.org/abs/2103.08134

【9】 Classifying Cycling Hazards in Egocentric Data
标题：在以自我为中心的数据中对骑行危险进行分类
作者：Jayson Haebich,Christian Sandor,Alvaro Cassinelli
链接：https://arxiv.org/abs/2103.08102

【10】 Versailles-FP dataset: Wall Detection in Ancient
标题：凡尔赛-FP数据集：古代的墙体检测
作者：Wassim Swaileh,Dimitrios Kotzinos,Suman Ghosh,Michel Jordan,Son Vu,Yaguan Qian
备注：16 pages, submitted to ICDAR2021 conference
链接：https://arxiv.org/abs/2103.08064

【11】 Towards Generalizable and Robust Face Manipulation Detection via Bag-of-local-feature
标题：基于局部特征包的泛化鲁棒人脸操作检测
作者：Changtao Miao,Qi Chu,Weihai Li,Tao Gong,Wanyi Zhuang,Nenghai Yu
备注：5 pages, 2 figures
链接：https://arxiv.org/abs/2103.07915

【12】 Principled Ultrasound Data Augmentation for Classification of Standard Planes
标题：用于标准平面分类的原则性超声数据增强
作者：Lok Hin Lee,Yuan Gao,J. Alison Noble
备注：Information Processing in Medical Imaging (IPMI) 2021
链接：https://arxiv.org/abs/2103.07895

【13】 Learning a Proposal Classifier for Multiple Object Tracking
标题：用于多目标跟踪的建议分类器的学习
作者：Peng Dai,Renliang Weng,Wongun Choi,Changshui Zhang,Zhangping He,Wei Ding
备注：Accepted at CVPR 2021, Poster, EEE/CVF Conference on Computer Vision and Pattern Recognition
链接：https://arxiv.org/abs/2103.07889

【14】 Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesis
标题：多模态弹道预测的三个步骤：模态聚类、分类和综合
作者：Jianhua Sun,Yuxuan Li,Hao-Shu Fang,Cewu Lu
链接：https://arxiv.org/abs/2103.07854

【15】 ReDet: A Rotation-equivariant Detector for Aerial Object Detection
标题：REDET：一种用于空中目标检测的旋转等变检测器
作者：Jiaming Han,Jian Ding,Nan Xue,Gui-Song Xia
备注：Accepted by CVPR2021
链接：https://arxiv.org/abs/2103.07733

【16】 Which K-Space Sampling Schemes is good for Motion Artifact Detection in Magnetic Resonance Imaging?
标题：哪种K空间采样方案适合磁共振成像中的运动伪影检测？
作者：Mohammad Reza Mohebbian,Ekta Walia,Khan A. Wahid
链接：https://arxiv.org/abs/2103.08516

[分割/语义相关]：

【1】 Interpretability of a Deep Learning Model in the Application of Cardiac MRI Segmentation with an ACDC Challenge Dataset
标题：深度学习模型在ACDC挑战数据集心脏MRI分割中的可解释性
作者：Adrianna Janik,Jonathan Dodd,Georgiana Ifrim,Kris Sankaran,Kathleen Curran
链接：https://arxiv.org/abs/2103.08590

【2】 Margin Preserving Self-paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation
标题：基于域自适应的保边自步长对比学习在医学图像分割中的应用
作者：Zhizhe Liu,Zhenfeng Zhu,Shuai Zheng,Yang Liu,Jiayu Zhou,Yao Zhao
备注：12 pages, 10 figures, submitted to JBHI
链接：https://arxiv.org/abs/2103.08454

【3】 Adapt Everywhere: Unsupervised Adaptation of Point-Clouds and Entropy Minimisation for Multi-modal Cardiac Image Segmentation
标题：无处不在的适应：多模态心脏图像分割的点云无监督自适应和熵最小化
作者：Sulaiman Vesal,Mingxuan Gu,Ronak Kosti,Andreas Maier,Nishant Ravikumar
备注：Accepted for publication in IEEE Transactions on Medical Imaging (IEEE TMI)
链接：https://arxiv.org/abs/2103.08219

【4】 Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion
标题：模块化交互式视频对象分割：交互掩码、传播和差异感知融合
作者：Ho Kei Cheng,Yu-Wing Tai,Chi-Keung Tang
备注：Accepted to CVPR 2021. Project page: this https URL
链接：https://arxiv.org/abs/2103.07941

【5】 Image Segmentation Methods for Non-destructive testing Applications
标题：一种用于无损检测的图像分割方法
作者：EL-Hachemi Guerrout,Ramdane Mahiou,Randa Boukabene,Assia Ouali
备注：10 pages, 3 figures, the article is just accepted in the conference JERI 2020 but the conference stopped because of Covid so the article non published
链接：https://arxiv.org/abs/2103.07754

[人脸相关]：

【1】 3DCaricShop: A Dataset and A Baseline Method for Single-view 3D Caricature Face Reconstruction
标题：3DCaricShop：单视图三维漫画人脸重建的数据集和基线方法
作者：Yuda Qiu,Xiaojie Xu,Lingteng Qiu,Yan Pan,Yushuang Wu,Weikai Chen,Xiaoguang Han
备注：CVPR 2021. Project page:this https URL
链接：https://arxiv.org/abs/2103.08204

【2】 LARNet: Lie Algebra Residual Network for Profile Face Recognition
标题：LARNet：用于侧面人脸识别的李代数残差网络
作者：Xiaolong Yang
链接：https://arxiv.org/abs/2103.08147

【3】 An Efficient Multitask Neural Network for Face Alignment, Head Pose Estimation and Face Tracking
标题：一种用于人脸对齐、头部姿态估计和人脸跟踪的高效多任务神经网络
作者：Jiahao Xia,Haimin Zhang,Shiping Wen,Shuo Yang,Min Xu
备注：13 pages, 9 figures
链接：https://arxiv.org/abs/2103.07615

【4】 Cross-Domain Similarity Learning for Face Recognition in Unseen Domains
标题：未知域中人脸识别的跨域相似度学习
作者：Masoud Faraki,Xiang Yu,Yi-Hsuan Tsai,Yumin Suh,Manmohan Chandraker
备注：Accepted to CVPR'21
链接：https://arxiv.org/abs/2103.07503

[GAN/对抗式/生成式相关]：

【1】 Generating Synthetic Handwritten Historical Documents With OCR Constrained GANs
标题：用OCR约束的GAN生成合成手写历史文档
作者：Lars Vögtlin,Manuel Drazyk,Vinaychandran Pondenkandath,Michele Alberti,Rolf Ingold
链接：https://arxiv.org/abs/2103.08236

【2】 DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network
标题：DIVCO：基于对比生成对抗性网络的多样化条件图像合成
作者：Rui Liu,Yixiao Ge,Ching Lam Choi,Xiaogang Wang,Hongsheng Li
备注：To appear at CVPR2021
链接：https://arxiv.org/abs/2103.07893

【3】 Unsupervised Image Transformation Learning via Generative Adversarial Networks
标题：基于产生式对抗网络的无监督图像变换学习
作者：Kaiwen Zha,Yujun Shen,Bolei Zhou
备注：14 pages, 15 figures, 2 tables
链接：https://arxiv.org/abs/2103.07751

【4】 Generating Unrestricted Adversarial Examples via Three Parameters
标题：通过三个参数生成不受限制的对抗性实例
作者：Hanieh Naderi,Leili Goli,Shohreh Kasaei
链接：https://arxiv.org/abs/2103.07640

【5】 Fine-grained MRI Reconstruction using Attentive Selection Generative Adversarial Networks
标题：基于注意力选择生成对抗网络的细粒度MRI重建
作者：Jingshuai Liu,Mehrdad Yaghoobi
备注：5 pages, 2 figures, 1 table, 22 references
链接：https://arxiv.org/abs/2103.07672

[行为/时空/光流/姿态/运动]：

【1】 Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Driving
标题：利用自主驾驶的时空特征提高跨域迁移学习的泛化能力
作者：Shivam Akhauri,Laura Zheng,Tom Goldstein,Ming Lin
备注：6 pages, 3 figures, 8 tables
链接：https://arxiv.org/abs/2103.08116

【2】 MBAPose: Mask and Bounding-Box Aware Pose Estimation of Surgical Instruments with Photorealistic Domain Randomization
标题：MBAPose：基于真实感区域随机化的手术器械掩模和包围盒姿态估计
作者：Masakazu Yoshimura,Murilo Marques Marinho,Kanako Harada,Mamoru Mitsuishi
备注：8 pages, submitted to IROS2021
链接：https://arxiv.org/abs/2103.08105

[半/弱/无监督相关]：

【1】 Cascaded Feature Warping Network for Unsupervised Medical Image Registration
标题：用于无监督医学图像配准的级联特征扭曲网络
作者：Liutong Zhang,Lei Zhou,Ruiyang Li,Xianyu Wang,Boxuan Han,Hongen Liao
备注：Accepted by ISBI2021
链接：https://arxiv.org/abs/2103.08213

【2】 R-PointHop: A Green, Accurate and Unsupervised Point Cloud Registration Method
标题：R-PointHop：一种绿色、准确、无监督的点云配准方法
作者：Pranav Kadam,Min Zhang,Shan Liu,C. -C. Jay Kuo
备注：13 pages, 11 figures
链接：https://arxiv.org/abs/2103.08129

【3】 Semi-Supervised Video Deraining with Dynamic Rain Generator
标题：基于动态雨量发生器的半监督视频降维
作者：Zongsheng Yue,Jianwen Xie,Qian Zhao,Deyu Meng
备注：Accepted by CVPR 2021
链接：https://arxiv.org/abs/2103.07939

[跟踪相关]：

【1】 Multi-Object Tracking using Poisson Multi-Bernoulli Mixture Filtering for Autonomous Vehicles
标题：基于泊松多贝努利混合滤波的自主车辆多目标跟踪
作者：Su Pang,Hayder Radha
链接：https://arxiv.org/abs/2103.07783

【2】 A review of machine learning in processing remote sensing data for mineral exploration
标题：机器学习在矿产勘查遥感数据处理中的应用综述
作者：Hojat Shirmard,Ehsan Farahbakhsh,Dietmar Muller,Rohitash Chandra
备注：74 pages, 5 figures, 1 table
链接：https://arxiv.org/abs/2103.07678

【3】 Lasry-Lions Envelopes and Nonconvex Optimization: A Homotopy Approach
标题：Lasry-Lions包络与非凸优化：一种同伦方法
作者：Miguel Simões,Andreas Themelis,Panagiotis Patrinos
备注：5 pages, 2 figures, submitted
链接：https://arxiv.org/abs/2103.08533

[迁移学习/domain/主动学习/自适应]：

【1】 Online Learning of Objects through Curiosity-Driven Active Learning
标题：通过好奇心驱动的主动学习实现对象的在线学习
作者：Ali Ayub,Alan R. Wagner
备注：Presented at IEEE RoMan 2020 (Workshop on Lifelong Learning for Long-term Human-Robot Interaction (LL4LHRI)). arXiv admin note: text overlap with arXiv:2009.05105
链接：https://arxiv.org/abs/2103.07758

【2】 Towards Learning Food Portion From Monocular Images With Cross-Domain Feature Adaptation
标题：基于跨域特征自适应的单目图像食物部分学习方法
作者：Zeman Shao,Shaobo Fang,Runyu Mao,Jiangpeng He,Janine Wright,Deborah Kerr,Carol Jo Boushey,Fengqing Zhu
链接：https://arxiv.org/abs/2103.07562

【3】 Uncertainty-guided Model Generalization to Unseen Domains
标题：不确定性引导的模型向未知域的泛化
作者：Fengchun Qiao,Xi Peng
备注：In CVPR 2021 (13 pages including supplementary material)
链接：https://arxiv.org/abs/2103.07531

[裁剪/量化/加速相关]：

【1】 RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs
标题：RANP：3DCNN初始化时的资源感知神经元修剪
作者：Zhiwei Xu,Thalaiyasingam Ajanthan,Vibhav Vineet,Richard Hartley
备注：this is an extension of our 3DV2020 conference paper RANP. arXiv admin note: substantial text overlap with arXiv:2010.02488
链接：https://arxiv.org/abs/2103.08457

【2】 A Few-Shot Learning Approach for Accelerated MRI via Fusion of Data-Driven and Subject-Driven Priors
标题：基于数据驱动和主题驱动先验融合的加速MRIFew-Shot学习方法
作者：Salman Ul Hassan Dar,Mahmut Yurt,Tolga Çukur
备注：Accepted for presentation at the 29th Annual Meeting of the International Society of Magnetic Resonance in Medicine (ISMRM)
链接：https://arxiv.org/abs/2103.07790

【3】 Untrained networks for compressive lensless photography
标题：用于压缩无透镜摄影的未经训练的网络
作者：Kristina Monakhova,Vi Tran,Grace Kuo,Laura Waller
备注：16 pages, 8 figures
链接：https://arxiv.org/abs/2103.07609

[视频理解VQA/caption等]：

【1】 VMAF And Variants: Towards A Unified VQA
标题：VMAF及其变体：迈向统一的VQA
作者：Pankaj Topiwala,Wei Dai,Jiangfeng Pian
链接：https://arxiv.org/abs/2103.07770

[数据集dataset]：

【1】 OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding
标题：OCID-Ref：一种用于杂波场景接地的嵌入式语言三维机器人数据集
作者：Ke-Jyun Wang,Yun-Hsuan Liu,Hung-Ting Su,Jen-Wei Wang,Yu-Siang Wang,Winston H. Hsu,Wen-Chin Chen
备注：NAACL 2021
链接：https://arxiv.org/abs/2103.07679

【2】 I-Nema: A Biological Image Dataset for Nematode Recognition
标题：I-NEMA：一种用于线虫识别的生物图像数据集
作者：Xuequan Lu,Yihao Wang,Sheldon Fung,Xue Qing
链接：https://arxiv.org/abs/2103.08335

【3】 The QXS-SAROPT Dataset for Deep Learning in SAR-Optical Data Fusion
标题：用于SAR-光学数据融合深度学习的QXS-SAROPT数据集
作者：Meiyu Huang,Yao Xu,Lixin Qian,Weili Shi,Yaqin Zhang,Wei Bao,Nan Wang,Xuejiao Liu,Xueshuang Xiang
链接：https://arxiv.org/abs/2103.08259

[超分辨率]：

【1】 Learning Frequency-aware Dynamic Network for Efficient Super-Resolution
标题：学习频率感知动态网络实现有效的超分辨率
作者：Wenbin Xie,Dehua Song,Chang Xu,Chunjing Xu,Hui Zhang,Yunhe Wang
链接：https://arxiv.org/abs/2103.08357

[点云]：

【1】 Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding
标题：Cycle4Completion：使用带缺失区域编码的循环变换完成不成对的点云
作者：Xin Wen,Zhizhong Han,Yan-Pei Cao,Pengfei Wan,Wen Zheng,Yu-Shen Liu
备注：Accepted to CVPR 2021
链接：https://arxiv.org/abs/2103.07838

[深度depth相关]：

【1】 Beyond Image to Depth: Improving Depth Prediction using Echoes
标题：超越图像到深度：使用回波改进深度预测
作者：Kranti Kumar Parida,Siddharth Srivastava,Gaurav Sharma
备注：To appear in CVPR 2021
链接：https://arxiv.org/abs/2103.08468

【2】 Dilated Fully Convolutional Neural Network for Depth Estimation from a Single Image
标题：膨胀全卷积神经网络在单幅图像深度估计中的应用
作者：Binghan Li,Yindong Hua,Yifeng Liu,Mi Lu
链接：https://arxiv.org/abs/2103.07570

[3D/3D重建等相关]：

【1】 Monte Carlo Scene Search for 3D Scene Understanding
标题：基于蒙特卡罗场景搜索的三维场景理解
作者：Shreyas Hampali,Sinisa Stekovic,Sayan Deb Sarkar,Chetan Srinivasa Kumar,Friedrich Fraundorfer,Vincent Lepetit
备注：Accepted to CVPR 2021. We will upload the final paper version after March 29th
链接：https://arxiv.org/abs/2103.07969

【2】 Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images
标题：RGBD中的Reference-It-in-RGBD：一种自下而上的RGBD图像三维视觉接地方法
作者：Haolin Liu,Anran Lin,Xiaoguang Han,Lei Yang,Yizhou Yu,Shuguang Cui
链接：https://arxiv.org/abs/2103.07894

[OCR]：

【1】 uTHCD: A New Benchmarking for Tamil Handwritten OCR
标题：uTHCD：泰米尔语手写OCR的新基准
作者：Noushath Shaffi,Faizal Hajamohideen
备注：30 pages, 18 figures
链接：https://arxiv.org/abs/2103.07676

[其他视频相关]：

【1】 Siamese Network Features for Endoscopy Image and Video Localization
标题：用于内窥镜图像和视频定位的暹罗网络特征
作者：Mohammad Reza Mohebbian,Seyed Shahim Vedaei,Khan A. Wahid,Paul Babyn
链接：https://arxiv.org/abs/2103.08504

【2】 Boundary Proposal Network for Two-Stage Natural Language Video Localization
标题：两阶段自然语言视频本地化的边界建议网络
作者：Shaoning Xiao,Long Chen,Songyang Zhang,Wei Ji,Jian Shao,Lu Ye,Jun Xiao
备注：AAAI 2021
链接：https://arxiv.org/abs/2103.08109

[其他]：

【1】 RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching
标题：RoRD：用于局部特征匹配的旋转鲁棒描述符和正交视图
作者：Udit Singh Parihar,Aniket Gujarathi,Kinal Mehta,Satyajit Tourani,Sourav Garg,Michael Milford,K. Madhava Krishna
备注：Under Review at IROS. Project Page: this https URL
链接：https://arxiv.org/abs/2103.08573

【2】 Is Medical Chest X-ray Data Anonymous?
标题：医学胸片数据是匿名的吗？
作者：Kai Packhäuser,Sebastian Gündel,Nicolas Münster,Christopher Syben,Vincent Christlein,Andreas Maier
备注：Submission to Nature
链接：https://arxiv.org/abs/2103.08562

【3】 Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise
标题：带乘性激活噪声神经网络的无采样变分推理
作者：Jannik Schmitt,Stefan Roth
链接：https://arxiv.org/abs/2103.08497

【4】 Uncertainty-Based Biological Age Estimation of Brain MRI Scans
标题：基于不确定性的脑MRI扫描生物年龄估计
作者：Karim Armanious,Sherif Abdulatif,Wenbin Shi,Tobias Hepp,Sergios Gatidis,Bin Yang
备注：Accepted in ICASSP 2021. 5 pages, 4 figures. arXiv admin note: substantial text overlap with arXiv:2009.10765
链接：https://arxiv.org/abs/2103.08491

【5】 Machine Learning for Nondestructive Wear Assessment in Large Internal Combustion Engines
标题：机器学习在大型内燃机磨损无损评估中的应用
作者：Christoph Angermann,Steinbjörn Jónsson,Markus Haltmeier,Adéla Moravová,Christian Laubichler,Constantin Kiesling,Martin Kober,Wolfgang Fimml
链接：https://arxiv.org/abs/2103.08482

【6】 Deep Consensus Learning
标题：深度共识学习
作者：Wei Sun,Tianfu Wu
备注：Work in progress
链接：https://arxiv.org/abs/2103.08475

【7】 Beyond ANN: Exploiting Structural Knowledge for Efficient Place Recognition
标题：超越人工神经网络：利用结构化知识实现有效的地点识别
作者：Stefan Schubert,Peer Neubert,Peter Protzel
备注：Accepted for publication at International Conference on Robotics and Automation (ICRA) 2021. This is the submitted version
链接：https://arxiv.org/abs/2103.08366

【8】 Knowledge driven Description Synthesis for Floor Plan Interpretation
标题：知识驱动的平面布置图解译描述综合
作者：Shreya Goyal,Chiranjoy Chattopadhyay,Gaurav Bhatnagar
备注：19 pages, 18 Figure
链接：https://arxiv.org/abs/2103.08298

【9】 GRIHA: Synthesizing 2-Dimensional Building Layouts from Images Captured using a Smart Phone
标题：Griha：利用智能手机拍摄的图像合成二维建筑布局
作者：Shreya Goyal,Naimul Khan,Chiranjoy Chattopadhyay,Gaurav Bhatnagar
备注：19 pages, 22 Figures, 4 Tables
链接：https://arxiv.org/abs/2103.08297

【10】 Rotation Coordinate Descent for Fast Globally Optimal Rotation Averaging
标题：快速全局最优旋转平均的旋转坐标下降法
作者：Álvaro Parra,Shin-Fang Chng,Tat-Jun Chin,Anders Eriksson,Ian Reid
备注：Accepted to CVPR 2021 as an oral presentation
链接：https://arxiv.org/abs/2103.08292

【11】 DeepOPG: Improving Orthopantomogram Finding Summarization with Weak Supervision
标题：DeepOPG：在弱监督的情况下改进正射影像查找总结
作者：Tzu-Ming Hsu,Yin-Chih Wang
链接：https://arxiv.org/abs/2103.08290

【12】 Trust Your IMU: Consequences of Ignoring the IMU Drift
标题：相信你的IMU：忽略IMU漂移的后果
作者：Marcus Valtonen Örnhag,Patrik Persson,Mårten Wadenbäck,Kalle Åström,Anders Heyden
链接：https://arxiv.org/abs/2103.08286

【13】 Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation
标题：在自学中提炼自己：通过自我知识提炼提炼特色
作者：Mingi Ji,Seungjae Shin,Seunghyun Hwang,Gibeom Park,Il-Chul Moon
备注：CVPR 2021
链接：https://arxiv.org/abs/2103.08273

【14】 Learning Compositional Representation for 4D Captures with Neural ODE
标题：用神经ODE学习4D图像的成分表示
作者：Boyan Jiang,Yinda Zhang,Xingkui Wei,Xiangyang Xue,Yanwei Fu
备注：Accepted by CVPR2021. Supplementary material, project webpage, data and codes are coming soon
链接：https://arxiv.org/abs/2103.08271

【15】 DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Network
标题：DMN4：基于区分互最近邻神经网络的少机会学习
作者：Yang Liu,Tu Zheng,Jie Song,Deng Cai,Xiaofei He
备注：10 pages, 6 figures
链接：https://arxiv.org/abs/2103.08160

【16】 Exploring Genetic-histologic Relationships in Breast Cancer
标题：乳腺癌遗传-组织学关系的探讨
作者：Ruchi Chauhan,PK Vinod,CV Jawahar
备注：Accepted at International Symposium of Biomedical Imaging (ISBI) 2021
链接：https://arxiv.org/abs/2103.08082

【17】 Pushing the Limits of Capsule Networks
标题：突破胶囊网络的极限
作者：Prem Nair,Rohan Doshi,Stefan Keselj
链接：https://arxiv.org/abs/2103.08074

【18】 Deep Tiling: Texture Tile Synthesis Using a Deep Learning Approach
标题：深度平铺：基于深度学习的纹理平铺合成
作者：Vasilis Toulatzis,Ioannis Fudos
链接：https://arxiv.org/abs/2103.07992

【19】 TransFG: A Transformer Architecture for Fine-grained Recognition
标题：TransFG：一种面向细粒度识别的转换器结构
作者：Ju He,Jieneng Chen,Shuai Liu,Adam Kortylewski,Cheng Yang,Yutong Bai,Changhu Wang,Alan Yuille
链接：https://arxiv.org/abs/2103.07976

【20】 SaNet: Scale-aware neural Network for Parsing Multiple Spatial Resolution Aerial Images
标题：SANET：基于尺度感知的多空间分辨率航空影像解析神经网络
作者：Libo Wang
链接：https://arxiv.org/abs/2103.07935

【21】 Bangla Handwritten Digit Recognition and Generation
标题：孟加拉手写数字识别与生成
作者：Md Fahim Sikder
备注：Proceedings of International Joint Conference on Computational Intelligence
链接：https://arxiv.org/abs/2103.07905

【22】 Multi-view data capture for dynamic object reconstruction using handheld augmented reality mobiles
标题：使用手持增强现实移动设备进行动态对象重建的多视图数据捕获
作者：M. Bortolon,L. Bazzanella,F. Poiesi
备注：Accepted in Journal of Real-Time Image Processing
链接：https://arxiv.org/abs/2103.07883

【23】 Radar Camera Fusion via Representation Learning in Autonomous Driving
标题：自主驾驶中基于表征学习的雷达摄像机融合
作者：Xu Dong,Binnan Zhuang,Yunxiang Mao,Langechuan Liu
链接：https://arxiv.org/abs/2103.07825

【24】 ORStereo: Occlusion-Aware Recurrent Stereo Matching for 4K-Resolution Images
标题：ORStereo：4K分辨率图像的遮挡感知递归立体匹配
作者：Yaoyu Hu,Wenshan Wang,Huai Yu,Weikun Zhen,Sebastian Scherer
备注：Submitted to International Conference on Intelligent Robots and Systems (IROS) 2021
链接：https://arxiv.org/abs/2103.07798

【25】 Reconsidering Representation Alignment for Multi-view Clustering
标题：重新考虑多视图聚类中的表示对齐问题
作者：Daniel J. Trosten,Sigurd Løkse,Robert Jenssen,Michael Kampffmeyer
备注：To appear in CVPR 2021. Code available at this https URL
链接：https://arxiv.org/abs/2103.07738

【26】 NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering using RGB Cameras
标题：NeuralHumanFVV：使用RGB摄像机的实时神经体积人体性能绘制
作者：Xin Suo,Yuheng Jiang,Pei Lin,Yingliang Zhang,Kaiwen Guo,Minye Wu,Lan Xu
链接：https://arxiv.org/abs/2103.07700

【27】 PhotoApp: Photorealistic Appearance Editing of Head Portraits
标题：PhotoApp：头像的真实感外观编辑
作者：Mallikarjun B R,Ayush Tewari,Abdallah Dib,Tim Weyrich,Bernd Bickel,Hans-Peter Seidel,Hanspeter Pfister,Wojciech Matusik,Louis Chevallier,Mohamed Elgharib,Christian Theobalt
备注：this http URL
链接：https://arxiv.org/abs/2103.07658

【28】 Ensemble Learning with Manifold-Based Data Splitting for Noisy Label Correction
标题：基于流形数据分割的噪声标签校正集成学习
作者：Hao-Chiang Shao,Hsin-Chieh Wang,Weng-Tai Su,Chia-Wen Lin
链接：https://arxiv.org/abs/2103.07641

【29】 Potential Escalator-related Injury Identification and Prevention Based on Multi-module Integrated System for Public Health
标题：基于多模块公共卫生集成系统的自动扶梯潜在伤害识别与预防
作者：Zeyu Jiao,Huan Lei,Hengshan Zong,Yingjie Cai,Zhenyu Zhong
备注：16pages, 13figures. submitted to MACHINE VISION AND APPLICATIONS
链接：https://arxiv.org/abs/2103.07620

【30】 Student-Teacher Learning from Clean Inputs to Noisy Inputs
标题：师生从清洁输入到噪声输入的学习
作者：Guanzhe Hong,Zhiyuan Mao,Xiaojun Lin,Stanley H. Chan
备注：Published at the Conference on Computer Vision and Pattern Recognition (CVPR 2021)
链接：https://arxiv.org/abs/2103.07600

【31】 Revisiting ResNets: Improved Training and Scaling Strategies
标题：重访ResNet：改进的培训和扩展策略
作者：Irwan Bello,William Fedus,Xianzhi Du,Ekin D. Cubuk,Aravind Srinivas,Tsung-Yi Lin,Jonathon Shlens,Barret Zoph
链接：https://arxiv.org/abs/2103.07579

【32】 DiaRet: A browser-based application for the grading of Diabetic Retinopathy with Integrated Gradients
标题：DiaRet：一个基于浏览器的集成梯度的糖尿病视网膜病变分级应用
作者：Shaswat Patel,Maithili Lohakare,Samyak Prajapati,Shaanya Singh,Nancy Patel
链接：https://arxiv.org/abs/2103.08501

【33】 COVID-19 Infection Localization and Severity Grading from Chest X-ray Images
标题：基于胸部X线图像的冠状病毒感染定位及严重程度分级
作者：Anas M. Tahir,Muhammad E. H. Chowdhury,Amith Khandakar,Tawsifur Rahman,Yazan Qiblawey,Uzair Khurshid,Serkan Kiranyaz,Nabil Ibtehaz,M Shohel Rahman,Somaya Al-Madeed,Khaled Hameed,Tahir Hamid,Sakib Mahmud,Maymouna Ezeddin
备注：30 pages, 5 figures, 4 tables
链接：https://arxiv.org/abs/2103.07985

【34】 Progressive residual learning for single image dehazing
标题：渐进残差学习在单幅图像去噪中的应用
作者：Yudong Liang,Bin Wang,Jiaying Liu,Deyu Li,Yuhua Qian,Wenqi Ren
链接：https://arxiv.org/abs/2103.07973

【35】 Early Prediction and Diagnosis of Retinoblastoma Using Deep Learning Techniques
标题：深度学习技术在视网膜母细胞瘤早期预测和诊断中的应用
作者：C. Anand Deva Durai,T Jemima Jebaseeli,Salem Alelyani,Azath Mubharakali
链接：https://arxiv.org/abs/2103.07622

【36】 Mining Artifacts in Mycelium SEM Micrographs
标题：菌丝体扫描电镜照片中的矿物质
作者：Thaicia Stona de Almeida
备注：7 pages, 9 figures
链接：https://arxiv.org/abs/2103.07573

机器翻译，仅供参考；“机构”信息仅供参考