计算机视觉/图像处理每日论文速递[06.05]

同步公众号(arXiv每日学术速递),欢迎关注,感谢支持哦~

[检测分类相关]:

【1】 Semi-supervised and Unsupervised Methods for Heart Sounds Classification in Restricted Data Environments
受限数据环境下心音分类的半监督和非监督方法
作者: Balagopal Unnikrishnan, Matthew Chin Heng Chua
链接:arxiv.org/abs/2006.0261

【2】 CircleNet: Anchor-free Detection with Circle Representation
CircleNet:具有圆表示的无锚点检测
作者: Haichun Yang, Yuankai Huo
链接:arxiv.org/abs/2006.0247

【3】 Pathological myopia classification with simultaneous lesion segmentation using deep learning
基于深度学习的同时病变分割的病理性近视分类
作者: Ruben Hemelings, Patrick De Boever
链接:arxiv.org/abs/2006.0281

【4】 Deep Sequential Feature Learning in Clinical Image Classification of Infectious Keratitis
深度序列特征学习在感染性角膜炎临床图像分类中的应用
作者: Yesheng Xu, Yu-Feng Yao
链接:arxiv.org/abs/2006.0266

【5】 DFR-TSD: A Deep Learning Based Framework for Robust Traffic Sign Detection Under Challenging Weather Conditions
DFR-TSD:一种基于深度学习的具有挑战性天气条件下的鲁棒交通标志检测框架
作者: Sabbir Ahmed, Md. Kamrul Hasan
链接:arxiv.org/abs/2006.0257

【6】 Exploration of Interpretability Techniques for Deep COVID-19 Classification using Chest X-ray Images
利用胸部X射线图像探讨COVID-19深层分类的可解释性技术
作者: Soumick Chatterjee, Andreas Nürnberger
链接:arxiv.org/abs/2006.0257

[分割/语义相关]:

【1】 LRNNet: A Light-Weighted Network with Efficient Reduced Non-Local Operation for Real-Time Semantic Segmentation
LRNNet:一种轻量级网络,具有高效减少的非局部操作,用于实时语义分割
作者: Weihao Jiang, Hongtao Lu
备注:To appear in icme2020workshop(MMC)
链接:arxiv.org/abs/2006.0270

【2】 Boundary-assisted Region Proposal Networks for Nucleus Segmentation
用于细胞核分割的边界辅助区域建议网络
作者: Shengcong Chen, Dacheng Tao
备注:Early Acception by MICCAI 2020
链接:arxiv.org/abs/2006.0269

【3】 Evaluation of Deep Segmentation Models for the Extraction of Retinal Lesions from Multi-modal Retinal Images
用于从多模式视网膜图像中提取视网膜病变的深度分割模型的评价
作者: Taimur Hassan, Naoufel Werghi
链接:arxiv.org/abs/2006.0266

【4】 Uncertainty quantification in medical image segmentation with Normalizing Flows
基于归一化流程的医学图像分割中的不确定性量化
作者: Raghavendra Selvan, Akshay Pai
链接:arxiv.org/abs/2006.0268

【5】 Automated segmentation of retinal fluid volumes from structural and angiographic optical coherence tomography using deep learning
使用深度学习从结构和血管造影光学相干断层扫描中自动分割视网膜液量
作者: Yukun Guo, Yali Jia
链接:arxiv.org/abs/2006.0256

[人脸相关]:

【1】 Look Locally Infer Globally: A Generalizable Face Anti-Spoofing Approach
全局局部推断:一种可推广的人脸反欺骗方法
作者: Debayan Deb, Anil K. Jain
链接:arxiv.org/abs/2006.0283

【2】 GAN-Based Facial Attractiveness Enhancement
基于GaN的面部吸引力增强
作者: Yuhongze Zhou, Qinjie Xiao
链接:arxiv.org/abs/2006.0276

[GAN/对抗式/生成式相关]:

【1】 Multiple Generative Adversarial Networks Analysis for Predicting Photographers' Retouching
预测摄影师修饰效果的多重生成对抗网络分析
作者: Marc Bickel, Sébastien Gachoud
链接:arxiv.org/abs/2006.0292

【2】 Image Augmentations for GAN Training
用于GaN训练的图像增强
作者: Zhengli Zhao, Han Zhang
链接:arxiv.org/abs/2006.0259

[行为/时空/光流/姿态/运动]:

【1】 A Siamese Neural Network with Modified Distance Loss For Transfer Learning in Speech Emotion Recognition
语音情感识别中迁移学习的改进距离损失暹罗神经网络
作者: Kexin Feng, Theodora Chaspari
备注:AffCon@AAAI-20; Presented at AAAI-20 W1: Affective Content Analysis
链接:arxiv.org/abs/2006.0300

【2】 Event-based visual place recognition with ensembles of spatio-temporal windows
时空窗口集成的基于事件的视觉地点识别
作者: Tobias Fischer, Michael Milford
链接:arxiv.org/abs/2006.0282

[半/弱/无监督相关]:

【1】 Unsupervised Depth Learning in Challenging Indoor Video: Weak Rectification to Rescue
挑战室内视频中的无监督深度学习:对救援的弱纠正
作者: Jia-Wang Bian, Ian Reid
链接:arxiv.org/abs/2006.0270

【2】 Simple Unsupervised Multi-Object Tracking
简单无监督多目标跟踪
作者: Shyamgopal Karthik, Vineet Gandhi
链接:arxiv.org/abs/2006.0260

[跟踪相关]:

【1】 COMET: Context-Aware IoU-Guided Network for Small Object Tracking
COMET:上下文感知IOU引导的小目标跟踪网络
作者: Seyed Mojtaba Marvasti-Zadeh, Li Cheng
链接:arxiv.org/abs/2006.0259

[迁移学习/domain/主动学习/自适应]:

【1】 Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
用于领域自适应对象重新识别的混合记忆自定步长对比学习
作者: Yixiao Ge, Hongsheng Li
链接:arxiv.org/abs/2006.0271

[裁剪/量化/加速相关]:

【1】 A Polynomial Neural network with Controllable Precision and Human-Readable Topology II: Accelerated Approach Based on Expanded Layer
精度可控且拓扑可读的多项式神经网络II:基于扩展层的加速方法
作者: Gang Liu, Jing Wang
链接:arxiv.org/abs/2006.0290

[Re-id相关]:

【1】 FastReID: A Pytorch Toolbox for Real-world Person Re-identification
FastReID:一个用于真实世界中人的重新识别的Pytorch工具箱
作者: Lingxiao He, Tao Mei
链接:arxiv.org/abs/2006.0263

[数据集dataset]:

【1】 Problems of dataset creation for light source estimation
光源估计的数据集创建问题
作者: E.I. Ershov, A.V. Savchik
链接:arxiv.org/abs/2006.0269

[深度depth相关]:

【1】 A Survey on Deep Learning Techniques for Stereo-based Depth Estimation
基于立体的深度估计深度学习技术综述
作者: Hamid Laga, Mohammed Bennamoun
链接:arxiv.org/abs/2006.0253

[3D/3D重建等相关]:

【1】 Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning
Info3D:基于互信息最大化和对比学习的3D对象表示学习
作者: Aditya Sanghi
链接:arxiv.org/abs/2006.0259

[其他视频相关]:

【1】 Visual Summarization of Lecture Video Segments for Enhanced Navigation
增强导航的讲座视频片段的可视摘要
作者: Mohammad Rajiur Rahman, Shishir Shah
链接:arxiv.org/abs/2006.0243

[其他]:

【1】 Visually Guided Sound Source Separation using Cascaded Opponent Filter Network
基于级联对手滤波网络的视觉制导声源分离
作者: Lingyu Zhu, Esa Rahtu
链接:arxiv.org/abs/2006.0302

【2】 RarePlanes: Synthetic Data Takes Flight
RarePlanes:合成数据起飞
作者: Jacob Shermeyer, Daeil Kim
链接:arxiv.org/abs/2006.0296

【3】 2D Image Features Detector And Descriptor Selection Expert System
二维图像特征检测与描述符选择专家系统
作者: Ibon Merino, Basilio Sierra
链接:arxiv.org/abs/2006.0293

【4】 A Computational Model of Early Word Learning from the Infant's Point of View
从婴儿的角度看早期单词学习的计算模型
作者: Satoshi Tsutsui, Chen Yu
备注:Accepted by Annual Conference of the Cognitive Science Society (CogSci) 2020. (Oral Acceptance Rate = 177/811 = 22%)
链接:arxiv.org/abs/2006.0280

【5】 Height estimation from single aerial images using a deep ordinal regression network
使用深序回归网络从单个航空图像中估计高度
作者: Xiang Li, Yi Fang
链接:arxiv.org/abs/2006.0280

【6】 MFPP: Morphological Fragmental Perturbation Pyramid for Black-Box Model Explanations
MFPP:黑盒模型解释的形态碎片扰动金字塔
作者: Qing Yang, Yuan Zhu
链接:arxiv.org/abs/2006.0265

【7】 The Importance of Prior Knowledge in Precise Multimodal Prediction
先验知识在精确多模态预测中的重要性
作者: Sergio Casas, Raquel Urtasun
链接:arxiv.org/abs/2006.0263

【8】 Image Completion and Extrapolation with Contextual Cycle Consistency
具有上下文周期一致性的图像补全和外推
作者: Sai Hemanth Kasaraneni, Abhishek Mishra
备注:This paper has been accepted to 2020 IEEE International Conference on Image Processing (ICIP 2020)
链接:arxiv.org/abs/2006.0262

【9】 Phasic dopamine release identification using ensemble of AlexNet
使用AlexNet集成识别时相多巴胺释放
作者: Luca Patarnello, Loris Nanni
链接:arxiv.org/abs/2006.0253

【10】 Assessing Intelligence in Artificial Neural Networks
人工神经网络中的智能评估
作者: Nicholas J. Schaub, Nathan Hotaling
链接:arxiv.org/abs/2006.0290

【11】 Overcoming Overfitting and Large Weight Update Problem in Linear Rectifiers: Thresholded Exponential Rectified Linear Units
克服线性整流器中的过拟合和大权值更新问题:阈值指数整流线性单元
作者: Vijay Pandey
链接:arxiv.org/abs/2006.0279

【12】 M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training
M3P:通过多任务多语言多模态预培训学习通用表示
作者: Haoyang Huang, Ming Zhou
链接:arxiv.org/abs/2006.0263

【13】 Robust Automatic Whole Brain Extraction on Magnetic Resonance Imaging of Brain Tumor Patients using Dense-Vnet
基于Dense-vNet的脑肿瘤患者磁共振成像的健壮全脑提取
作者: Sara Ranjbar (1), USA)
链接:arxiv.org/abs/2006.0262

机器翻译,仅供参考

发布于 2020-06-05 10:02