天天看点

arXiv每日推荐-5.5:计算机视觉/图像处理每日论文速递

同步公众号(arXiv每日学术速递)

[检测分类相关]:

【1】 Automated eye disease classification method from anterior eye image using anatomical structure focused image classification technique

利用解剖结构聚焦图像分类技术从眼前眼图像中自动分类眼病的方法

作者: Masahiro Oda, Kensaku Mori

备注:Accepted paper as a poster presentation at SPIE Medical Imaging 2020, Houston, TX, USA

链接:https://arxiv.org/abs/2005.01433

【2】 Monitoring COVID-19 social distancing with person detection and tracking via fine-tuned YOLO v3 and Deepsort techniques

通过微调的YOLO v3和Deepsort技术监控COVID-19社会距离与人员检测和跟踪

作者: Narinder Singh Punn, Sonali Agarwal

链接:https://arxiv.org/abs/2005.01385

【3】 One-Shot Image Classification by Learning to Restore Prototypes

学习恢复原型的单次图像分类

作者: Wanqi Xue, Wei Wang

备注:Published as a conference paper in AAAI 2020

链接:https://arxiv.org/abs/2005.01234

【4】 Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities

遥感图像场景分类遇到深度学习:挑战、方法、基准和机会

作者: Gong Cheng, Gui-Song Xia

备注:20 pages, 10 figures

链接:https://arxiv.org/abs/2005.01094

【5】 Joint-SRVDNet: Joint Super Resolution and Vehicle Detection Network

联合-SRVDNet:联合超分辨率和车辆检测网络

作者: Moktari Mostofa, Nasser M. Nasrabadi

链接:https://arxiv.org/abs/2005.00983

【6】 BeCAPTCHA-Mouse: Synthetic Mouse Trajectories and Improved Bot Detection

BeCAPTCHA-Mouse:合成鼠标轨迹和改进的Bot检测

作者: Alejandro Acien, Ruben Vera-Rodriguez

链接:https://arxiv.org/abs/2005.00890

【7】 A Deep Convolutional Neural Network for COVID-19 Detection Using Chest X-Rays

用于胸部X射线检测COVID-19的深卷积神经网络

作者: Pedro R. A. S. Bassi, Romis Attux

链接:https://arxiv.org/abs/2005.01578

【8】 An Adaptive Enhancement Based Hybrid CNN Model for Digital Dental X-ray Positions Classification

一种基于自适应增强的混合CNN模型用于数字牙科X线位置分类

作者: Yaqi Wang, Wuteng Qi

链接:https://arxiv.org/abs/2005.01509

【9】 A cascade network for Detecting COVID-19 using chest x-rays

使用胸部X射线检测COVID-19的级联网络

作者: Dailin Lv, Yaqi Wang

链接:https://arxiv.org/abs/2005.0146

【10】 NTIRE 2020 Challenge on Image and Video Deblurring

NTIRE 2020图像和视频去模糊挑战

作者: Seungjun Nah, Kyoung Mu Lee

备注:To be published in CVPR 2020 Workshop (New Trends in Image Restoration and Enhancement)

链接:https://arxiv.org/abs/2005.01244

【11】 Minor Privacy Protection Through Real-time Video Processing at the Edge

通过边缘实时视频处理保护次要隐私

作者: Meng Yuan, Yunxi Dong

备注:Accepted by the 2nd International Workshop on Smart City Communication and Networking at the ICCCN 2020

链接:https://arxiv.org/abs/2005.0117

【12】 Investigating Class-level Difficulty Factors in Multi-label Classification Problems

多标签分类问题中类层次难度因素的研究

作者: Mark Marsden, Noel E O’Connor

备注:Published in ICME 2020

链接:https://arxiv.org/abs/2005.00430

【13】 Aggregation and Finetuning for Clothes Landmark Detection

用于服装地标检测的聚集和微调

作者: Tzu-Heng Lin

链接:https://arxiv.org/abs/2005.00419

【14】 Sequence Information Channel Concatenation for Improving Camera Trap Image Burst Classification

一种改进相机陷阱图像突发分类的序列信息通道级联方法

作者: Bhuvan Malladihalli Shashidhara, Megan Hazen

链接:https://arxiv.org/abs/2005.00116

【15】 On-board Deep-learning-based Unmanned Aerial Vehicle Fault Cause Detection and Identification

基于机载深度学习的无人机故障原因检测与识别

作者: Vidyasagar Sadhu, Dario Pompili

链接:https://arxiv.org/abs/2005.00336

【16】 Unsupervised Lesion Detection via Image Restoration with a Normative Prior

基于规范先验的图像恢复无监督病变检测

作者: Xiaoran Chen, Ender Konukoglu

备注:Extended version of ‘Unsupervised Lesion Detection via Image Restoration with a Normative Prior’ (MIDL2019)

链接:https://arxiv.org/abs/2005.0003

【17】 Occlusion resistant learning of intuitive physics from videos

视频中直观物理的抗遮挡学习

作者: Ronan Riochet, Emmanuel Dupoux

链接:https://arxiv.org/abs/2005.0006

【18】 A Fast 3D CNN for Hyperspectral Image Classification

一种用于高光谱图像分类的快速3DCNN

作者: Muhammad Ahmad

链接:https://arxiv.org/abs/2004.14152

【19】 DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data

DR-SPAAM:一种用于2D距离数据中人物检测的空间注意和自回归模型

作者: Dan Jia, Bastian Leibe

链接:https://arxiv.org/abs/2004.1407

【20】 Video Contents Understanding using Deep Neural Networks

基于深度神经网络的视频内容理解

作者: Mohammadhossein Toutiaee, John A. Miller

链接:https://arxiv.org/abs/2004.1395

【21】 Event-based Robotic Grasping Detection with Neuromorphic Vision Sensor and Event-Stream Dataset

基于神经形态视觉传感器和事件流数据集的机器人抓取检测

作者: Bin Li, Zichen Liang

链接:https://arxiv.org/abs/2004.13652

【22】 Data Augmentation Imbalance For Imbalanced Attribute Classification

不平衡属性分类的数据增强不平衡

作者: Xiaying Bai, Shengmei Shen

链接:https://arxiv.org/abs/2004.13628

【23】 Exploring Self-attention for Image Recognition

图像识别中的自我注意探索

作者: Hengshuang Zhao, Vladlen Koltun

备注:CVPR 2020, Code available at this https URL

链接:https://arxiv.org/abs/2004.13621

【24】 Multivariate Confidence Calibration for Object Detection

目标检测的多变量置信校正

作者: Fabian Küppers, Anselm Haselhoff

备注:Accepted on CVPR 2020 Workshop: “2nd Workshop on Safe Artificial Intelligence for Automated Driving (SAIAD)”

链接:https://arxiv.org/abs/2004.13546

【25】 Real-Time Apple Detection System Using Embedded Systems With Hardware Accelerators: An Edge AI Application

使用嵌入式系统和硬件加速器的实时苹果检测系统:Edge AI应用

作者: Vittorio Mazzia, Marcello Chiaberge

链接:https://arxiv.org/abs/2004.13410

【26】 Gradient-Induced Co-Saliency Detection

梯度诱导的共同显著性检测

作者: Zhao Zhang, Ming-Ming Cheng

链接:https://arxiv.org/abs/2004.13364

【27】 SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing

SCRDet+:通过实例级特征去噪和旋转损失平滑检测小、杂乱和旋转的对象

作者: Xue Yang, Tao He

链接:https://arxiv.org/abs/2004.13316

【28】 Trainable Activation Function Supported CNN in Image Classification

支持CNN的可训练激活函数在图像分类中的应用

作者: Zhaohe Liao

链接:https://arxiv.org/abs/2004.13271

【29】 The Problem of Fragmented Occlusion in Object Detection

目标检测中的碎片遮挡问题

作者: Julian Pegoraro, Roman Pflugfelder

备注:accepted by the Austrian Joint Computer Vision and Robotics Workshop 2020 (this https URL)

链接:https://arxiv.org/abs/2004.1307

继续阅读