同步wx订阅号(arXiv每日论文速递),支持后台回复'search 关键词'查询相关的最新论文。有些许帮助的话,麻烦关注一下哦(* ̄rǒ ̄)
cs.CV 方向,今日共计38篇
[检测分类相关]:
【1】 Deformable Tube Network for Action Detection in Videos
用于视频中动作检测的可变形管网络
作者: Wei Li, Changhu Wang
链接:https://arxiv.org/abs/1907.01847
【2】 Unsupervised Anomalous Trajectory Detection for Crowded Scenes
拥挤场景下的无监督异常轨迹检测
作者: Deepan Das, Deepak Mishra
链接:https://arxiv.org/abs/1907.01717
【3】 Robust Cochlear Modiolar Axis Detection in CT
CT中稳健的耳蜗磨牙轴检测
作者: Wilhelm Wimmer, Hervé Delingette
备注:Accepted for MICCAI 2019
链接:https://arxiv.org/abs/1907.01870
【4】 Automated Detection and Type Classification of Central Venous Catheters in Chest X-Rays
胸部X线片中心静脉导管的自动检测和分型
作者: Vaishnavi Subramanian, Tanveer Syeda-Mahmood
备注:Accepted to Medical Image Computing and Computer Assisted Intervention (MICCAI) 2019
链接:https://arxiv.org/abs/1907.01656
[分割/语义相关]:
【1】 Anatomically Consistent Segmentation of Organs at Risk in MRI with Convolutional Neural Networks
基于卷积神经网络的MRI危险器官解剖一致性分割
作者: Pawel Mlynarski, Nicholas Ayache
链接:https://arxiv.org/abs/1907.02003
【2】 Supervised Uncertainty Quantification for Segmentation with Multiple Annotations
多注解分割的监督不确定性量化
作者: Shi Hu, Max Welling
备注:Accepted as a conference paper to MICCAI 2019
链接:https://arxiv.org/abs/1907.01949
【3】 Deep Attentive Features for Prostate Segmentation in 3D Transrectal Ultrasound
三维经直肠超声前列腺分割的深度注意特征
作者: Yi Wang, Dong Ni
链接:https://arxiv.org/abs/1907.01743
[GAN/对抗式/生成式相关]:
【1】 Robust Synthesis of Adversarial Visual Examples Using a Deep Image Prior
基于深度图像先验的对抗性视觉实例鲁棒综合
作者: Thomas Gittings, John Collomosse
备注:Accepted to BMVC 2019
链接:https://arxiv.org/abs/1907.01996
【2】 Semi-supervised Image Attribute Editing using Generative Adversarial Networks
基于生成对抗性网络的半监督图像属性编辑
作者: Yahya Dogan, Hacer Yalim Keles
链接:https://arxiv.org/abs/1907.01841
【3】 Cascade Attention Guided Residue Learning GAN for Cross-Modal Translation
用于跨模态翻译的级联注意引导残差学习GaN
作者: Bin Duan, Yan Yan
链接:https://arxiv.org/abs/1907.01826
【4】 Mask Embedding in conditional GAN for Guided Synthesis of High Resolution Images
在条件GaN中嵌入掩模用于高分辨率图像的引导合成
作者: Yinhao Ren, Joseph Lo
链接:https://arxiv.org/abs/1907.01710
【5】 Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack
具有快速自适应边界攻击的最小扭曲对抗性实例
作者: Francesco Croce, Matthias Hein
链接:https://arxiv.org/abs/1907.02044
【6】 Accelerating Deconvolution on Unmodified CNN Accelerators for Generative Adversarial Networks -- A Software Approach
生成对抗性网络中未修饰CNN加速器的加速反卷积-一种软件方法
作者: Kaijie Tu
链接:https://arxiv.org/abs/1907.01773
[行为/时空/光流/姿态/运动]:
【1】 Novel evaluation of surgical activity recognition models using task-based efficiency metrics
使用基于任务的效率度量对手术活动识别模型的新评估
作者: Aneeq Zia, Anthony Jarc
链接:https://arxiv.org/abs/1907.02060
【2】 SkeletonNet: Shape Pixel to Skeleton Pixel
SkeletonNet:形状像素到骨架像素
作者: Sabari Nathan, Priya Kansal
备注:Published in CVPRw 2019
链接:https://arxiv.org/abs/1907.01683
[半/弱/无监督相关]:
【1】 Probabilistic Multilayer Regularization Network for Unsupervised 3D Brain Image Registration
无监督3D脑图像配准的概率多层正则化网络
作者: Lihao Liu, Pheng-Ann Heng
备注:Accepted at MICCAI 2019
链接:https://arxiv.org/abs/1907.01922
【2】 A Semi-Supervised Framework for Automatic Pixel-Wise Breast Cancer Grading of Histological Images
一种半监督的乳腺癌组织学图像像素智慧型自动分级框架
作者: Yanyuet Man, Han Bao
链接:https://arxiv.org/abs/1907.01696
[跟踪相关]:
【1】 Chasing Ghosts: Instruction Following as Bayesian State Tracking
追逐鬼魂:指令跟随贝叶斯状态跟踪
作者: Peter Anderson, Stefan Lee
链接:https://arxiv.org/abs/1907.02022
【2】 Tracking system of Mine Patrol Robot for Low Illumination Environment
低照度环境下的矿山巡逻机器人跟踪系统
作者: Shaoze You, Chaoquan Tang
链接:https://arxiv.org/abs/1907.01806
[裁剪/量化/加速相关]:
【1】 A Deep Image Compression Framework for Face Recognition
一种用于人脸识别的深度图像压缩框架
作者: Nai Bian, Bo Lei
链接:https://arxiv.org/abs/1907.01714
[其他视频相关]:
【1】 Simple vs complex temporal recurrences for video saliency prediction
用于视频显著性预测的简单时间递归与复杂时间递归
作者: Panagiotis Linardos, Kevin McGuinness
链接:https://arxiv.org/abs/1907.01869
【2】 Compositional Structure Learning for Sequential Video Data
序列视频数据的合成结构学习
作者: Kyoung-Woon On, Byoung-Tak Zhang
链接:https://arxiv.org/abs/1907.01709
[其他]:
【1】 Learning Landmarks from Unaligned Data using Image Translation
使用图像转换从未对齐的数据中学习地标
作者: Tomas Jakab, Andrea Vedaldi
链接:https://arxiv.org/abs/1907.02055
【2】 Using Deep Learning to Count Albatrosses from Space
利用深度学习对来自太空的信天翁进行计数
作者: Ellen Bowler, Michal Mackiewicz
备注:4 pages, 5 figures, to be presented at IEEE 2019 International Geoscience & Remote Sensing Symposium (IGARSS 2019), scheduled for July 28 - August 2, 2019
链接:https://arxiv.org/abs/1907.02040
【3】 Learning to Predict Robot Keypoints Using Artificially Generated Images
学习使用人工生成的图像预测机器人关键点
作者: Christoph Heindl, Josef Scharinger
链接:https://arxiv.org/abs/1907.01879
【4】 Super-Resolution of PROBA-V Images Using Convolutional Neural Networks
基于卷积神经网络的Proba-V图像超分辨率
作者: Marcus Märtens, Daniël Cox
链接:https://arxiv.org/abs/1907.01821
【5】 Attention routing between capsules
注意胶囊之间的路由
作者: Jaewoong Choi, Myungju Kang
链接:https://arxiv.org/abs/1907.01750
【6】 Hyper-Molecules: on the Representation and Recovery of Dynamical Structures, with Application to Flexible Macro-Molecular Structures in Cryo-EM
超分子:关于动态结构的表示和恢复,及其在Cryo-EM中柔性宏分子结构的应用
作者: Roy R. Lederman, Amit Singer
链接:https://arxiv.org/abs/1907.01589
【7】 Using AI for Economic Upliftment of Handicraft Industry
利用人工智能实现手工业的经济提升
作者: Nitya Raviprakash, Puneet Agrawal
链接:https://arxiv.org/abs/1907.02014
【8】 Learning with Known Operators reduces Maximum Training Error Bounds
与已知操作员的学习减少了最大训练误差范围
作者: Andreas K. Maier, Silke Christiansen
链接:https://arxiv.org/abs/1907.01992
【9】 On-Device Neural Net Inference with Mobile GPUs
使用移动GPU的设备上神经网络推理
作者: Juhyun Lee, Matthias Grundmann
备注:Computer Vision and Pattern Recognition Workshop: Efficient Deep Learning for Computer Vision 2019
链接:https://arxiv.org/abs/1907.01989
【10】 Intrinsic Image Popularity Assessment
内在形象受欢迎程度评估
作者: Keyan Ding, Shiqi Wang
备注:Accepted by ACM Multimedia 2019
链接:https://arxiv.org/abs/1907.01985
【11】 FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search
FairNAS:重新思考权重分担的评价公平性神经架构搜索
作者: Xiangxiang Chu, Jixiang Li
链接:https://arxiv.org/abs/1907.01845
【12】 Intrinsic Calibration of Depth Cameras for Mobile Robots using a Radial Laser Scanner
使用径向激光扫描仪的移动机器人深度摄像机的内在校准
作者: David Zuñiga-Noël, Javier Gonzalez-Jimenez
备注:Submitted to the 18th International Conference on Computer Analysis of Images and Patterns. Project webpage (code): this http URL
链接:https://arxiv.org/abs/1907.01839
【13】 Calibration of fisheye camera using entrance pupil
利用入射光瞳标定鱼眼相机
作者: Peter Fasogbon, Emre Aksu
备注:5 pages, 4 figures, Accepted for publication at ICIP 2019
链接:https://arxiv.org/abs/1907.01759
【14】 Region-Manipulated Fusion Networks for Pancreatitis Recognition
区域操纵融合网络在胰腺炎识别中的应用
作者: Jian Wang, Weiqin Li
链接:https://arxiv.org/abs/1907.01744
【15】 Graph Neural Network for Interpreting Task-fMRI Biomarkers
用于解释任务-fMRI生物标记物的图神经网络
作者: Xiaoxiao Li, James S. Duncan
链接:https://arxiv.org/abs/1907.01661
【16】 Estimation of Absolute States of Human Skeletal Muscle via Standard B-Mode Ultrasound Imaging and Deep Convolutional Neural Networks
通过标准B型超声成像和深度卷积神经网络估计人体骨骼肌的绝对状态
作者: Ryan J. Cunningham, Ian D. Loram
链接:https://arxiv.org/abs/1907.01649
翻译:腾讯翻译君